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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Ambul
    0.89
     والان
    0.88
     ваши
    0.76
     would
    0.74
     madde
    0.73
    뼈
    0.71
    명이
    0.70
     khas
    0.70
     বাহুল্য
    0.70
    ↻
    0.70
    POSITIVE LOGITS
    t
    1.04
    tım
    0.90
    ing
    0.84
    ých
    0.83
    습니다
    0.82
    ین
    0.78
    s
    0.78
    ει
    0.77
    ມ
    0.77
    er
    0.76
    Act Density 0.000%

    No Known Activations