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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that introduce or declare code constructs—e.g. keywords or identifiers used in function/method definitions, class/module declarations, property or field declarations, and similar code‐structure markers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     arrayWith
    -0.06
     lastIndex
    -0.06
     bordered
    -0.06
    อฟ
    -0.06
     Tổng
    -0.06
    ＊
    -0.06
    _tiles
    -0.06
    】
    -0.06
    ्
    -0.06
    .CommandText
    -0.06
    POSITIVE LOGITS
     topl
    0.07
     прик
    0.07
     Selenium
    0.07
    	finally
    0.07
     APPLE
    0.07
    ırak
    0.06
    enin
    0.06
    LBL
    0.06
    ůj
    0.06
    unca
    0.06
    Act Density 0.044%

    No Known Activations