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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Trabalho
    0.93
     Акча
    0.91
    鈁
    0.91
     gême
    0.91
     чемпион
    0.90
     görüntü
    0.89
     perfeita
    0.89
     dinheiro
    0.88
     amerikanischen
    0.86
     acero
    0.85
    POSITIVE LOGITS
     just
    0.78
     might
    0.76
     the
    0.74
     this
    0.73
    ,
    0.72
     –
    0.71
     damage
    0.71
     Sco
    0.71
    息
    0.71
    （
    0.69
    Act Density 0.000%

    No Known Activations