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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Э
    0.86
     StandardScaler
    0.76
     الث
    0.75
     Ş
    0.73
     И
    0.73
     Ту
    0.72
     Ш
    0.70
     Г
    0.70
     Дж
    0.70
     Unavailable
    0.69
    POSITIVE LOGITS
    ounces
    0.80
     বাংলাকে
    0.78
    gap
    0.76
    नों
    0.75
    from
    0.74
    北海道
    0.74
    నికి
    0.74
    acción
    0.74
    不管是
    0.73
    allowSlide
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.