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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     clickView
    0.48
    ヴ
    0.47
    ាញ
    0.46
    ഘ
    0.46
    തായി
    0.45
    സ്ട്ര
    0.45
    कर्षण
    0.45
    亟
    0.44
    ௐ
    0.43
    നു
    0.43
    POSITIVE LOGITS
     means
    4.44
     mean
    4.09
     означает
    3.95
     meaning
    3.91
    means
    3.91
     Means
    3.78
     significa
    3.73
     berarti
    3.72
     означа
    3.70
    Means
    3.63
    Act Density 1.192%

    No Known Activations