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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    事实上
    0.77
    梆
    0.75
    获得
    0.71
     numar
    0.71
     brav
    0.71
     farlo
    0.71
    吐槽
    0.71
    ☣
    0.71
     anonym
    0.70
    وروب
    0.70
    POSITIVE LOGITS
     స
    0.99
    ки
    0.86
    ز
    0.83
    nez
    0.82
    kitchen
    0.79
     forl
    0.78
    ны
    0.77
    chutz
    0.75
    containers
    0.75
    гр
    0.74
    Act Density 0.000%

    No Known Activations