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

    Neuronpedia

    INDEX
    Explanations

    domain aggregate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fool
    0.43
    imp
    0.41
     Sylvia
    0.39
    ู่
    0.38
    差し
    0.38
    Ph
    0.37
     vulnerable
    0.37
    preprocess
    0.37
     Impressions
    0.37
     SEL
    0.37
    POSITIVE LOGITS
    Aggregate
    0.73
     Aggregate
    0.71
     aggregate
    0.70
     aggregates
    0.69
     Domain
    0.66
     domain
    0.64
    Commands
    0.62
    Domain
    0.60
    CommandHandler
    0.60
    aggregate
    0.59
    Act Density 0.013%

    No Known Activations