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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ة
    0.52
    o
    0.50
    ing
    0.47
    ud
    0.45
    1
    0.44
     ሁለት
    0.39
    og
    0.39
    ı
    0.39
    ag
    0.39
     and
    0.38
    POSITIVE LOGITS
    نا
    0.39
    وا
    0.34
    ﻤ
    0.32
    مل
    0.31
    ्यूर
    0.31
    逖
    0.31
    Downloading
    0.31
    nvarchar
    0.30
     mendapatkan
    0.30
    тивов
    0.30
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.