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

    Neuronpedia

    INDEX
    Explanations

    html doctype declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     exclu
    1.10
    openzeppelin
    0.98
    clientY
    0.95
     numéro
    0.93
     ved
    0.91
     findViewById
    0.90
    }"]
    0.89
     consist
    0.89
    },"
    0.89
     dacă
    0.86
    POSITIVE LOGITS
     Są
    1.13
    ה
    1.09
    ровой
    1.06
    ੀ
    1.05
    া
    1.04
    ры
    1.03
    са
    1.01
     बल
    1.01
    사의
    1.01
    률
    1.01
    Act Density 0.002%

    No Known Activations