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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases and elements related to personal expressions or inquiries

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

    Code, equations or mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    explicit series, many people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tròn
    -0.36
     silla
    -0.33
    คล
    -0.32
     daze
    -0.32
     hoạch
    -0.32
     sillas
    -0.31
     aidant
    -0.31
    idorm
    -0.30
    asanjo
    -0.29
     CHAIR
    -0.28
    POSITIVE LOGITS
    RegressionTest
    0.89
     nahilalakip
    0.65
     OFDb
    0.59
     ModelExpression
    0.54
     ExecuteAsync
    0.54
    hyrchwyd
    0.54
    RuleContext
    0.53
    spesies
    0.50
    IUrlHelper
    0.50
    Jîn
    0.50
    Act Density 0.059%

    No Known Activations