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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ни
    0.92
     раза
    0.86
    ی
    0.79
    ния
    0.77
    ем
    0.75
    лиза
    0.74
     года
    0.73
     тариф
    0.72
     изображения
    0.72
     prepd
    0.71
    POSITIVE LOGITS
    cs
    0.73
    VOR
    0.72
    urus
    0.71
    SUN
    0.71
    LAR
    0.70
    瑷
    0.69
    ated
    0.68
    ancers
    0.68
    NUT
    0.68
    TS
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.