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

    Neuronpedia

    INDEX
    Explanations

    what one excels at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Effective
    0.46
     başarı
    0.45
    成功的
    0.44
     effective
    0.44
     успеш
    0.43
     வெற்ற
    0.43
    hourly
    0.43
    ದಲ
    0.42
     성공
    0.42
     کامیاب
    0.42
    POSITIVE LOGITS
     excel
    0.80
     Excel
    0.77
    Excel
    0.74
     shines
    0.65
     excels
    0.65
     excelled
    0.63
     shine
    0.62
     shining
    0.61
    excel
    0.61
     spreadsheets
    0.57
    Act Density 0.006%

    No Known Activations