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

    Neuronpedia

    INDEX
    Explanations

    Go code imports and type declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ADOR
    0.71
     সৃষ্ট
    0.69
    Adams
    0.67
    basicConfig
    0.65
     Taxi
    0.65
     अडानी
    0.65
    ходили
    0.65
    阑
    0.65
     Clooney
    0.65
    卢
    0.64
    POSITIVE LOGITS
     بالوں
    0.75
     soul
    0.69
     souls
    0.68
     ब्रश
    0.68
     doubted
    0.67
    എ
    0.66
     αι
    0.66
    utives
    0.65
     type
    0.65
    一是
    0.62
    Act Density 0.013%

    No Known Activations