Glossary · Term

neuron

← all terms

Definition

Plain language

One of the many tiny numerical slots inside an AI model — loosely named after brain cells, but really just a number that gets combined with thousands of others.

As stated in the literature

An individual scalar unit in a neural network's activation vector; in interpretability work, raw neurons are typically polysemantic — firing for unrelated concepts at once — which motivates recovering cleaner monosemantic features via dictionary learning rather than reading meaning off single neurons.

Also called: neurons, artificial neuron

Why it matters: Because individual neurons often mix unrelated concepts, you usually can't understand a model by reading them one at a time, which is why cleaner features are needed.

For example, a single neuron might light up both when the text mentions cats and when it mentions legal contracts, two things that have nothing to do with each other.

Heard on the show

“… objection early: that snap is measured without the lens — and a completely weight-based statistic, how neurons compose with directions, bumps at the same depth. …”
Episode 203 — The Thought a Model Doesn't Say — and the Lens That Reads It

Mentioned in 11 episodes

  1. 203
    The Thought a Model Doesn't Say — and the Lens That Reads It
  2. 185
    Aligned to Refuse, Built to Tap: When Phone Agents Know the Task Is a Crime and Do It Anyway
  3. 160
    Training an AI to Take Its Own Notes, So Its Future Self Works Better
  4. 153
    Catching a Lie From the Inside, When the Words Look Completely Honest
  5. 145
    Building Forgetting Into a Language Model With One Extra Line of Code
  6. 114
    Agents That Rewrite Their Own Weights Instead of Just Taking Notes
  7. 098
    Finding Millions of Readable Concepts Inside a Real, Deployed AI Model
  8. 062
    Treating Hallucinations as Exploits: A Gate-Based Architecture for Agent Safety
  9. 060
    When Splitting One Model Across Three Agents Doubles Its Accuracy
  10. 023
    Why a Small Agent Confidently Overwrites Memories It Doesn't Understand
  11. 018
    Language Models Compute the Rational Move, Then Override It

Related concepts

Related terms