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

    Neuronpedia

    INDEX
    Explanations

    lingerie

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $
    1.09
    การ
    1.08
    č
    1.07
    c
    1.04
    ä
    0.98
    o
    0.98
    -
    0.98
    지
    0.97
    ように
    0.95
     $
    0.95
    POSITIVE LOGITS
    ０
    1.33
    ل
    1.15
    yta
    1.14
    ۰
    1.12
     ພວກເຮົາ
    1.10
     Бал
    1.06
     وی
    1.05
    इका
    1.05
    ي
    1.03
    ؛
    1.02
    Act Density 0.000%

    No Known Activations