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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    को
    1.42
    in
    1.27
    িন
    1.27
    де
    1.24
    ка
    1.20
    д
    1.18
    ী
    1.16
    व्यापी
    1.16
    ール
    1.14
    ים
    1.14
    POSITIVE LOGITS
     It
    1.38
     If
    1.08
    ،
    1.02
    ش
    0.99
     They
    0.91
     on
    0.78
    and
    0.77
     Because
    0.76
    proofing
    0.76
     For
    0.76
    Act Density 0.000%

    No Known Activations