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

    Neuronpedia

    INDEX
    Explanations

    references to decision-making processes and conditional statements

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

    algebraic equations with variables

    np_acts-logits-general · gemini-2.5-flash-lite

    it detects code- or math-expression style tokens — control-flow and syntax markers, variable names, and numeric literals.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    wegs
    -0.42
     ailleurs
    -0.40
     tendencia
    -0.38
     Combinations
    -0.37
    tiful
    -0.36
     einst
    -0.36
     unders
    -0.36
     Tenden
    -0.36
    chop
    -0.35
     Rigby
    -0.35
    POSITIVE LOGITS
     ffilmiau
    0.54
    oredCriteria
    0.45
     OFDb
    0.40
    esgue
    0.40
     quæ
    0.40
    AndEndTag
    0.40
     ſtand
    0.39
    لينكات
    0.38
    expandindo
    0.38
    UnknownFields
    0.38
    Act Density 0.225%

    No Known Activations