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

    Neuronpedia

    INDEX
    Explanations

    Realization/Afterthought

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >C
    -0.07
    uards
    -0.07
    萎缩
    -0.07
    وضع
    -0.07
    ぶり
    -0.07
    ביק
    -0.06
    _PB
    -0.06
    ѹ
    -0.06
     saygı
    -0.06
    .MODEL
    -0.06
    POSITIVE LOGITS
    slug
    0.07
    (al
    0.07
     Hew
    0.06
    (parts
    0.06
     MongoClient
    0.06
     Frank
    0.06
    кус
    0.06
     Spotlight
    0.06
    otros
    0.06
    dney
    0.06
    Act Density 0.019%

    No Known Activations