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

    Neuronpedia

    INDEX
    Explanations

    fat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Palestinian
    -0.06
    [strlen
    -0.06
    !".
    -0.06
    gebn
    -0.06
     вступ
    -0.06
     получить
    -0.06
    cki
    -0.06
     fallen
    -0.06
     horsepower
    -0.06
    .getParam
    -0.06
    POSITIVE LOGITS
    confidence
    0.07
    ož
    0.07
    ulating
    0.07
    -purple
    0.07
    .Sys
    0.07
    /owl
    0.07
    リン
    0.07
     Agu
    0.06
     ×
    0.06
     selective
    0.06
    Act Density 0.003%

    No Known Activations