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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    。
    1.30
    ।
    1.19
     tanha
    0.93
     жана
    0.93
    ۔
    0.92
     größ
    0.89
     घटक
    0.87
    .
    0.84
     Meski
    0.84
     моём
    0.82
    POSITIVE LOGITS
    т
    1.45
    ت
    1.31
    us
    1.27
    X
    1.27
    תה
    1.21
    ל
    1.17
    A
    1.16
    ات
    1.16
    ers
    1.11
    es
    1.09
    Act Density 0.000%

    No Known Activations