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

    Neuronpedia

    INDEX
    Explanations

    job titles and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    be
    0.63
    ง่าย
    0.59
     was
    0.57
     forstå
    0.57
    专辑
    0.54
    quée
    0.54
    เล
    0.53
    Í
    0.52
    ற்புத
    0.52
    zeuge
    0.51
    POSITIVE LOGITS
     zonal
    0.66
     fitter
    0.66
    ٹرول
    0.65
    आरओ
    0.60
     доходов
    0.59
     purported
    0.57
     spirited
    0.55
     zoned
    0.55
     متوسط
    0.55
     தகவல்
    0.54
    Act Density 0.042%

    No Known Activations