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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    佥
    0.84
    会
    0.81
    ન
    0.78
    和
    0.77
    원
    0.77
    雰囲
    0.75
    挞
    0.73
    编码
    0.72
    зви
    0.72
    法
    0.72
    POSITIVE LOGITS
     всем
    1.02
     Bant
    1.02
     Hän
    0.90
     öffentlich
    0.90
     gastos
    0.89
     vollständig
    0.88
    uously
    0.88
     жены
    0.86
    ﺐ
    0.86
     Bildern
    0.86
    Act Density 0.000%

    No Known Activations