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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    тың
    1.13
    いた
    1.02
    daki
    0.99
    萏
    0.99
    IFICATION
    0.96
    muk
    0.96
    EMY
    0.94
     刘
    0.93
    OSPHER
    0.93
     Боль
    0.93
    POSITIVE LOGITS
    app
    0.93
    sized
    0.82
    signup
    0.80
    見る
    0.80
    i
    0.79
     marque
    0.79
     paperwork
    0.77
     sized
    0.76
    ا
    0.76
     toaster
    0.75
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.