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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     coin
    0.80
     餐
    0.79
    创
    0.74
    皇
    0.73
    厕
    0.72
    勛
    0.71
    हरु
    0.71
     Kapil
    0.71
    ̵
    0.70
     fast
    0.69
    POSITIVE LOGITS
     parámetros
    0.99
    тные
    0.94
     времени
    0.90
     такие
    0.85
     자신의
    0.83
     года
    0.83
    Cuál
    0.82
     собственных
    0.82
    Cuánt
    0.80
    Alliance
    0.79
    Act Density 0.000%

    No Known Activations