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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    empirical
    0.81
    epsilon
    0.76
    ijek
    0.72
     tbsp
    0.72
    ribu
    0.71
    isotropic
    0.71
    بی
    0.70
     ductility
    0.70
    一点
    0.68
    ัท
    0.67
    POSITIVE LOGITS
     возраст
    0.90
     chủ
    0.89
     является
    0.85
    йки
    0.84
     общего
    0.84
     Глав
    0.83
     пространства
    0.83
    உங்கள்
    0.80
     счастли
    0.80
    喈
    0.79
    Act Density 0.000%

    No Known Activations