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

    Neuronpedia

    INDEX
    Explanations

    technical terms/code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Съ
    0.67
    ню
    0.65
    sulf
    0.64
    Só
    0.63
    стер
    0.63
    тер
    0.61
    стов
    0.61
    getMessage
    0.61
    TAG
    0.60
    теры
    0.60
    POSITIVE LOGITS
    起動
    0.71
     Oracle
    0.66
    ادا
    0.65
     Apple
    0.64
     हुए
    0.63
     பு
    0.63
     ہوئے
    0.63
     ada
    0.62
     پ
    0.62
     ურთიერთ
    0.61
    Act Density 0.000%

    No Known Activations