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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ك
    1.27
    اً
    1.26
    از
    1.15
    č
    1.13
    ка
    1.13
    ه
    1.12
    estados
    1.10
    اج
    1.08
    其他
    1.06
    اع
    1.05
    POSITIVE LOGITS
     on
    1.27
    u
    1.16
    m
    1.11
     and
    0.98
     at
    0.89
    way
    0.89
     ৯
    0.88
    ם
    0.88
    ル
    0.85
    is
    0.85
    Act Density 0.000%

    No Known Activations