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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     самый
    0.92
     имеет
    0.90
     лучший
    0.89
     самая
    0.85
     самую
    0.83
     имеют
    0.81
     има
    0.77
     має
    0.77
    ഽ
    0.75
     MNRAS
    0.74
    POSITIVE LOGITS
    azie
    0.74
    ak
    0.73
    ز
    0.73
    écution
    0.72
    oon
    0.66
    y
    0.65
    زى
    0.65
    بلا
    0.65
    دم
    0.64
    別
    0.64
    Act Density 0.000%

    No Known Activations