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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Estou
    1.00
     Mã
    0.86
    estabelecimento
    0.84
     estou
    0.84
    Voir
    0.82
    Jangan
    0.82
     Função
    0.80
     Atual
    0.80
     Tính
    0.80
     estabelecimento
    0.77
    POSITIVE LOGITS
    ل
    0.82
     sprint
    0.76
    न
    0.74
    ку
    0.73
    ‌اند
    0.72
    ات
    0.71
     швидко
    0.67
    ра
    0.66
     spanning
    0.66
    ებისა
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.