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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    在
    1.70
    も
    1.66
    ও
    1.52
     in
    1.38
    도
    1.34
    もら
    1.33
    ال
    1.16
    いる
    1.16
    は
    1.16
    يد
    1.15
    POSITIVE LOGITS
    ни
    1.47
    ز
    1.21
    ко
    1.15
    ม
    1.13
    1.13
    м
    1.09
    cence
    1.05
    к
    1.05
    ного
    1.03
    อง
    1.00
    Act Density 0.000%

    No Known Activations