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

    Neuronpedia

    INDEX
    Explanations

    technical or factual

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    orgh
    0.73
    ⦿
    0.67
    ar
    0.66
    agin
    0.65
    ப்புற
    0.64
    pho
    0.63
    inol
    0.63
    booked
    0.63
    PUR
    0.62
    leiter
    0.62
    POSITIVE LOGITS
    льные
    0.68
    mıştır
    0.66
    貢
    0.66
     sayings
    0.64
     χαρακτη
    0.63
     Beiträge
    0.62
    mäßige
    0.62
    тный
    0.61
    льный
    0.61
     alve
    0.61
    Act Density 0.000%

    No Known Activations