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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    体育
    -0.07
     draft
    -0.07
    希
    -0.07
    _dims
    -0.06
     CN
    -0.06
    FER
    -0.06
    ToEnd
    -0.06
     needless
    -0.06
    ------------
    -0.06
    .readValue
    -0.06
    POSITIVE LOGITS
    에서는
    0.06
    .where
    0.06
    _mm
    0.06
    .Imp
    0.06
    ーフ
    0.06
    ?,
    0.06
    Matchers
    0.06
     Ign
    0.06
    NewProp
    0.06
     lista
    0.06
    Act Density 0.038%

    No Known Activations