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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    л
    0.91
    ל
    0.84
    лы
    0.82
    м
    0.80
    ো
    0.79
    docx
    0.78
    ল
    0.77
     esimerk
    0.76
     قدیم
    0.76
    ل
    0.75
    POSITIVE LOGITS
    贯彻
    0.71
    相应
    0.63
     başta
    0.63
     મળ
    0.62
    стане
    0.61
     hàm
    0.59
    ମ
    0.59
    Ğ
    0.58
    Provides
    0.57
     primacy
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.