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

    Neuronpedia

    INDEX
    Explanations

    some

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Be
    -0.07
    san
    -0.07
    _Exception
    -0.06
     Saunders
    -0.06
     объект
    -0.06
    .where
    -0.06
    孝
    -0.06
    olland
    -0.06
     tutti
    -0.06
    tutorial
    -0.06
    POSITIVE LOGITS
    _MEDIA
    0.07
    ','=
    0.06
    ]^
    0.06
     stringstream
    0.06
    тр
    0.06
    relu
    0.06
    Ó
    0.06
    uluğ
    0.06
     Χ
    0.06
    stringstream
    0.06
    Act Density 0.062%

    No Known Activations