Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash

    The neuron is specialized to spot Python code elements—especially method or function calls (names followed by “()”)—in the examples.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    code snippets demonstrating Python functions for data manipulation tasks.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _measure
    -0.07
    _expand
    -0.07
     King
    -0.07
     Reagan
    -0.06
     Western
    -0.06
     George
    -0.06
     elektrik
    -0.06
    ill
    -0.06
     收
    -0.06
    共和
    -0.06
    POSITIVE LOGITS
    ="";
↵
    0.06
    дн
    0.06
    .Link
    0.06
    ByText
    0.06
     rumor
    0.06
     tiểu
    0.06
     خوان
    0.06
    .Local
    0.06
    _util
    0.06
    ETweet
    0.06
    Act Density 0.096%

    No Known Activations