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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    г
    0.71
     inférieure
    0.70
    ila
    0.69
    ाब
    0.68
     coastline
    0.68
     establishment
    0.68
     freshman
    0.68
    ב
    0.68
     areas
    0.67
     negligible
    0.67
    POSITIVE LOGITS
     Дэ
    0.86
     зарубе
    0.81
    0.79
     उन
    0.79
    厛
    0.76
     ски
    0.75
    дных
    0.75
    有可能
    0.75
     рекоменду
    0.74
     испы
    0.74
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.