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

    Neuronpedia

    INDEX
    Explanations

    anything or anyone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۔
    2.56
    ן
    2.16
    。
    1.98
    וד
    1.78
    ৪
    1.75
    ской
    1.73
     manicure
    1.68
    ।
    1.67
     sexes
    1.66
     CBSE
    1.65
    POSITIVE LOGITS
    t
    2.16
    le
    2.03
    et
    1.97
    ्य
    1.87
     antérieure
    1.87
    ferencia
    1.84
    ha
    1.83
    ت
    1.82
    ons
    1.80
    on
    1.72
    Act Density 0.233%

    No Known Activations