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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    il
    0.33
    pt
    0.28
     M
    0.28
    uk
    0.27
    !`
    0.27
    !
    0.26
     V
    0.26
     albumen
    0.26
    !",
    0.26
    يلي
    0.26
    POSITIVE LOGITS
    به
    0.31
    是
    0.30
    ТО
    0.29
    of
    0.29
    дит
    0.29
    Ни
    0.27
     ilə
    0.27
    Не
    0.27
    Бу
    0.26
    我
    0.26
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.