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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ،
    1.06
    to
    0.95
     και
    0.93
     hvad
    0.89
    isiä
    0.87
    กับ
    0.86
     তাহলে
    0.83
     और
    0.82
     आणि
    0.82
     등의
    0.82
    POSITIVE LOGITS
    ל
    1.41
     as
    1.21
    ل
    1.14
    s
    1.13
    ল
    1.13
    લ
    1.13
    ના
    1.12
    ו
    1.10
    ا
    1.08
    ス
    1.04
    Act Density 0.000%

    No Known Activations