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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     be
    0.75
     Lizzy
    0.65
     Courts
    0.62
     calculators
    0.62
     completed
    0.60
    ซื้อ
    0.58
     aunts
    0.57
    태
    0.57
     court
    0.55
    껄
    0.55
    POSITIVE LOGITS
    ificação
    1.03
    ações
    0.86
    Iam
    0.84
     movimentos
    0.83
     Эк
    0.82
     чёр
    0.81
     הכ
    0.81
     namik
    0.81
     mág
    0.80
    tan
    0.79
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.