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

    Neuronpedia

    INDEX
    Explanations

    findContours

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.54
    ian
    1.13
    ine
    1.08
    al
    1.04
    ure
    1.01
    lington
    1.01
     to
    0.95
    niveau
    0.94
    el
    0.94
    ous
    0.94
    POSITIVE LOGITS
    ف
    1.67
    자
    1.26
    ي
    1.20
     a
    1.14
    ா
    1.14
    았
    1.11
    ру
    1.06
    ق
    1.04
    ко
    1.03
    اء
    1.01
    Act Density 0.000%

    No Known Activations