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

    Neuronpedia

    INDEX
    Explanations

    average historical returns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     финансо
    0.42
     financeiros
    0.42
     ఆర్థిక
    0.41
     FINANCE
    0.39
    逸
    0.38
     المالية
    0.38
    getSheet
    0.37
     বিপরীত
    0.37
    Finance
    0.36
    ја
    0.36
    POSITIVE LOGITS
     average
    0.90
     averaged
    0.87
     averages
    0.84
     평균
    0.84
     historically
    0.79
     averaging
    0.79
    平均
    0.78
     Average
    0.75
    Average
    0.73
     avg
    0.71
    Act Density 0.002%

    No Known Activations