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

    Neuronpedia

    INDEX
    Explanations

    code snippets and programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    مع
    1.18
    elajaran
    1.18
     Предпо
    1.16
     giants
    1.09
     Се
    1.07
     Сле
    1.04
     Fáb
    1.03
    蜡
    1.02
     Кла
    0.99
    sentence
    0.99
    POSITIVE LOGITS
    ccion
    1.14
    원으로
    1.05
    ct
    1.01
     extrapolate
    1.00
    -/
    0.99
    /
    0.99
    actment
    0.96
    alysis
    0.95
    $[\
    0.95
    ktop
    0.95
    Act Density 0.080%

    No Known Activations