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

    Neuronpedia

    INDEX
    Explanations

    square root calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ります
    0.42
    ელს
    0.40
    ydat
    0.40
    ynyl
    0.40
     ہوج
    0.39
    ্রেট
    0.39
    정한
    0.39
    iola
    0.39
    yti
    0.38
    テック
    0.37
    POSITIVE LOGITS
     Thessaloniki
    0.43
    Ge
    0.40
     Jac
    0.39
     Miss
    0.37
     Seven
    0.37
    Ap
    0.37
    Earth
    0.37
     Tonga
    0.36
    Trou
    0.36
    Ж
    0.36
    Act Density 0.002%

    No Known Activations