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

    Neuronpedia

    INDEX
    Explanations

    language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wie
    -0.07
     modem
    -0.06
    priv
    -0.06
    贵
    -0.06
    -Christian
    -0.06
    Christian
    -0.06
    Capture
    -0.06
    Wie
    -0.06
    020
    -0.06
    ورة
    -0.06
    POSITIVE LOGITS
    luž
    0.06
    _ENV
    0.06
    .Math
    0.06
    <TKey
    0.06
    ﾞﾞ
    0.06
    GREE
    0.06
    (mesh
    0.06
    (inp
    0.06
    (PDO
    0.06
     truths
    0.06
    Act Density 0.008%

    No Known Activations