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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Р
    0.92
    𒐪
    0.85
    秪
    0.80
     $)$
    0.80
    бліоте
    0.80
     Фі
    0.77
     Пі
    0.75
    льного
    0.73
     міста
    0.72
    hnen
    0.72
    POSITIVE LOGITS
     configurações
    0.78
    که
    0.77
    行為
    0.75
     notificações
    0.74
    ا
    0.73
     minst
    0.73
    னீ
    0.73
    کند
    0.72
    PLUGIN
    0.72
     endeavours
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.