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

    Neuronpedia

    INDEX
    Explanations

    Windows operating system

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tery
    0.82
    m
    0.80
    h
    0.72
     окно
    0.71
    ,
    0.71
    vore
    0.70
    v
    0.70
     ഇത
    0.68
    тся
    0.68
     ਇੱਕ
    0.68
    POSITIVE LOGITS
    ת
    1.01
    ה
    0.93
    া
    0.86
    ت
    0.85
    ه
    0.85
    고
    0.79
    ा
    0.78
    a
    0.77
    ে
    0.76
    ться
    0.75
    Act Density 0.010%

    No Known Activations