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

    Neuronpedia

    INDEX
    Explanations

    tabular data

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Diagn
    0.68
    Ripe
    0.66
     bottled
    0.63
    destructive
    0.63
    eqa
    0.61
     असुर
    0.60
     debilit
    0.59
     مرح
    0.59
    Analysis
    0.59
     Diagn
    0.59
    POSITIVE LOGITS
     által
    0.73
     הוד
    0.72
     كند
    0.72
     Balfour
    0.71
     بنگ
    0.69
    変数
    0.68
     Kuhn
    0.68
     কর্মী
    0.68
    ‍ह
    0.68
    ደም
    0.67
    Act Density 0.002%

    No Known Activations