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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ৬৮
    1.25
    #######
    1.13
    hydrogen
    1.10
    ীর
    1.09
    $-
    1.09
     ৩১
    1.08
    甫
    1.08
    임을
    1.08
     ceea
    1.06
     সংসদ
    1.06
    POSITIVE LOGITS
    нення
    1.29
    ق
    1.29
    ist
    1.22
    nå
    1.19
    m
    1.17
    cara
    1.16
    é
    1.16
    te
    1.13
    قية
    1.13
    es
    1.10
    Act Density 0.000%

    No Known Activations