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

    Neuronpedia

    INDEX
    Explanations

    margins, mashed, mass, massive, mashup, machine learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    1.07
     картины
    0.97
    머
    0.88
    𝕞
    0.88
    MEN
    0.87
    IN
    0.86
    Pa
    0.85
     комнаты
    0.84
    Were
    0.84
     lysates
    0.82
    POSITIVE LOGITS
    ри
    1.47
    ى
    1.06
    ли
    0.93
    يز
    0.88
    ก็
    0.87
    ו
    0.83
    re
    0.82
    ле
    0.80
    عة
    0.79
    ونه
    0.78
    Act Density 0.354%

    No Known Activations