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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ares
    0.93
     uds
    0.82
     окружающей
    0.82
    ut
    0.82
    cel
    0.81
    afood
    0.81
    ras
    0.81
    aren
    0.79
    si
    0.78
    hum
    0.78
    POSITIVE LOGITS
    و
    1.03
    AL
    0.92
    ا
    0.90
    AR
    0.89
    নি
    0.83
     PRODUCT
    0.81
    Outcome
    0.79
    ı
    0.78
    INTERNAL
    0.77
     Ajouter
    0.77
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.