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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    n
    1.00
    g
    0.98
    j
    0.95
    m
    0.89
    e
    0.87
    k
    0.86
    x
    0.84
    i
    0.84
    c
    0.84
    s
    0.83
    POSITIVE LOGITS
    дной
    0.71
    тся
    0.71
     برای
    0.69
    ணய
    0.67
    ському
    0.67
     والم
    0.66
    ਼
    0.66
     želite
    0.65
    kez
    0.65
    ဏ်
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.