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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     که
    1.20
    که
    1.19
     that
    1.13
    ING
    0.96
    צ
    0.95
    ുള്ള
    0.91
    ,’
    0.90
     që
    0.89
     was
    0.88
    IM
    0.88
    POSITIVE LOGITS
    u
    1.41
    其他
    1.20
    in
    1.16
    ل
    1.16
    л
    1.05
    uig
    0.93
    uia
    0.89
    "
    0.89
    inien
    0.85
    ла
    0.85
    Act Density 0.000%

    No Known Activations