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

    Neuronpedia

    INDEX
    Explanations

    writing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    べ
    1.21
     usize
    1.19
     mole
    1.10
     Theorem
    1.10
    െടു
    1.07
    ్‌
    1.07
    ണു
    1.07
    ol
    1.06
     cried
    1.05
    స్‌
    1.04
    POSITIVE LOGITS
     tắt
    1.32
    ಪೆ
    1.09
     சுவா
    1.09
    itatively
    1.05
     पढ़ी
    1.05
     pitted
    1.04
    పూర్
    1.03
     jakości
    1.00
     down
    0.99
    те
    0.99
    Act Density 0.209%

    No Known Activations