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

    Neuronpedia

    INDEX
    Explanations

    specific patterns and keywords related to tags and categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Two-letter abbreviations

    np_acts-logits-general · gemini-2.0-flash

    eg to gene or egocentric

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.71
    esModule
    -0.67
     ویکی‌پدی
    -0.66
     disambiguazione
    -0.64
    :✨
    -0.63
     useStyles
    -0.62
     Catawiki
    -0.62
    >*/
    -0.61
     imageNamed
    -0.60
    Diwedd
    -0.59
    POSITIVE LOGITS
    ging
    1.08
    gy
    0.95
    ged
    0.92
    ggg
    0.89
    gs
    0.87
    ger
    0.84
    gers
    0.84
    gin
    0.81
    gggg
    0.80
    GER
    0.79
    Act Density 0.921%

    No Known Activations