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

    Neuronpedia

    INDEX
    Explanations

    code and logic expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (=
    1.10
    }(\
    1.05
    、（
    1.05
    (“
    0.97
     (\"
    0.97
    ["
    0.96
    ({\
    0.96
    (\
    0.95
    )((
    0.95
    $(\
    0.95
    POSITIVE LOGITS
    ೇವೆ
    0.67
     ведет
    0.67
     लगाएं
    0.66
     pareil
    0.65
     такого
    0.65
     भ
    0.63
     encabez
    0.62
    يجي
    0.61
     naman
    0.61
    امام
    0.61
    Act Density 0.781%

    No Known Activations