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

    Neuronpedia

    INDEX
    Explanations

    parentheses, commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ку
    -0.07
    .updated
    -0.07
     مختصات
    -0.07
    relationships
    -0.07
     Wing
    -0.06
    _dispatch
    -0.06
     Kab
    -0.06
    に向
    -0.06
     Coin
    -0.06
     part
    -0.06
    POSITIVE LOGITS
     ساخته
    0.07
    Badge
    0.07
     söyledi
    0.06
     lizard
    0.06
    _ENDIAN
    0.06
    ：%
    0.06
    host
    0.06
     ром
    0.06
     вход
    0.06
    (pid
    0.06
    Act Density 0.008%

    No Known Activations