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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    programming code that includes control structures and handling of user input for mathematical operations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on closing curly-brace tokens (the “}” that ends code blocks).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    inus
    -0.06
    ليل
    -0.06
    *(-
    -0.06
    _expression
    -0.06
    ritz
    -0.06
     sera
    -0.06
    DI
    -0.06
    Thin
    -0.06
     caching
    -0.06
    removed
    -0.05
    POSITIVE LOGITS
    ="./
    0.07
     SIDE
    0.07
    _am
    0.06
    ("");
    0.06
     svob
    0.06
    販
    0.06
     couch
    0.06
     전문
    0.06
     нагруз
    0.06
    Foot
    0.06
    Act Density 0.021%

    No Known Activations