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

    Neuronpedia

    INDEX
    Explanations

    silver and contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ع
    1.25
    ان
    1.24
    س
    1.23
    ب
    1.18
    ض
    1.06
    ل
    1.05
    مل
    1.02
    י
    1.02
    ن
    1.01
    스
    1.01
    POSITIVE LOGITS
    Silver
    1.38
     silver
    1.16
     Silver
    1.13
     srebr
    1.13
    T
    1.12
    SIL
    1.10
     SILVER
    1.08
    H
    1.06
    W
    1.03
    P
    1.00
    Act Density 0.004%

    No Known Activations