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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    на
    0.73
    s
    0.64
    am
    0.59
    ের
    0.57
    та
    0.53
    ်
    0.50
    ка
    0.50
     has
    0.48
    јединачна
    0.48
    have
    0.46
    POSITIVE LOGITS
    .
    0.57
     for
    0.55
    0.53
    ۔
    0.48
    í
    0.47
    ó
    0.45
    ü
    0.45
    ő
    0.45
    ла
    0.41
    تج
    0.41
    Act Density 0.000%

    No Known Activations