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

    Neuronpedia

    INDEX
    Explanations

    server context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    1.36
    لي
    1.29
    اك
    1.28
    ايا
    1.26
    مي
    1.24
    اين
    1.16
    人
    1.16
     президен
    1.10
    ような
    1.09
     የተለያዩ
    1.09
    POSITIVE LOGITS
     server
    1.42
    K
    1.42
    J
    1.41
    T
    1.38
    et
    1.38
    V
    1.33
    ט
    1.23
    H
    1.22
     for
    1.19
     Server
    1.19
    Act Density 0.053%

    No Known Activations