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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     प
    1.13
    з
    1.06
     zab
    1.04
    나
    1.03
    തന്നെ
    1.01
     آموزش
    1.00
     попро
    0.98
    ما
    0.98
     ακόμη
    0.97
     امیدوار
    0.95
    POSITIVE LOGITS
    g
    1.39
     encased
    1.29
    kannya
    1.28
    uating
    1.22
    lur
    1.22
     subjected
    1.20
    es
    1.18
    𝒈
    1.16
     incapable
    1.16
    syringe
    1.15
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.