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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    しも
    0.95
     trasera
    0.83
     Trotz
    0.83
    おります
    0.81
    ҹ
    0.80
    일본
    0.78
    小
    0.77
     Cơ
    0.77
    अपने
    0.77
     masalah
    0.76
    POSITIVE LOGITS
    疇
    1.06
     haunts
    0.93
     ונ
    0.91
     overkill
    0.91
     Herod
    0.90
     showcases
    0.88
    iezan
    0.88
    uatan
    0.88
     الزاويه
    0.87
     invertible
    0.86
    Act Density 0.555%

    No Known Activations