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

    Neuronpedia

    INDEX
    Explanations

    android related code or text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    서
    1.98
    ように
    1.92
    ção
    1.67
    س
    1.58
    து
    1.57
     možnost
    1.54
    부터
    1.46
    ्स
    1.45
    하는
    1.43
    вання
    1.43
    POSITIVE LOGITS
    t
    2.05
    ra
    2.00
    re
    1.98
    é
    1.78
    ram
    1.73
    ли
    1.73
    od
    1.70
    न
    1.69
    the
    1.65
    ্র
    1.62
    Act Density 0.002%

    No Known Activations