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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     увла
    0.91
     работает
    0.86
     работо
    0.86
     работу
    0.84
     ascenso
    0.83
     ruido
    0.82
     А
    0.81
    ハウ
    0.80
     asuntos
    0.80
     hydroly
    0.80
    POSITIVE LOGITS
    ม
    0.72
    cs
    0.71
    ง
    0.68
    נדי
    0.68
    ম
    0.67
    り
    0.67
    it
    0.66
    тон
    0.66
    yer
    0.65
    onomy
    0.65
    Act Density 0.001%

    No Known Activations