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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    大
    1.16
    𝘢
    1.05
    垓
    1.02
    𝘸
    1.01
    heten
    1.00
    alaya
    0.99
    heaven
    0.99
     Historically
    0.97
    нома
    0.96
    unal
    0.94
    POSITIVE LOGITS
    nya
    1.09
    liery
    1.05
     incapac
    1.02
    Agregar
    1.01
    rs
    1.01
    lu
    1.01
    ায়ের
    0.99
    ן
    0.98
    ваць
    0.97
    BuildConfig
    0.97
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.