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

    Neuronpedia

    INDEX
    Explanations

    fill in the blankblank linesblank canvasblank paperblank values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     altos
    2.79
    ра
    2.73
    {}
    2.72
     judiciales
    2.61
    ного
    2.59
     للغاية
    2.59
    ٧
    2.56
    ɴ
    2.56
     bộ
    2.52
     laps
    2.51
    POSITIVE LOGITS
    ン
    4.80
    ت
    4.25
    ా
    3.50
    هی
    3.45
    ש
    3.27
    dır
    3.27
    oons
    3.27
    t
    3.18
    ed
    3.12
    دة
    2.99
    Act Density 0.013%

    No Known Activations