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

    Neuronpedia

    INDEX
    Explanations

    programming keywords and declarations

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

    code and structured data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.47
    addCriterion
    -0.35
    Décès
    -0.34
     rights
    -0.33
     stea
    -0.33
     capability
    -0.32
     bug
    -0.32
     suel
    -0.31
    LookAnd
    -0.31
     ranked
    -0.31
    POSITIVE LOGITS
     ویکی‌پدی
    0.56
    ArrowToggle
    0.56
     Wikimedijinoj
    0.52
     Chwiliwch
    0.51
    oredCriteria
    0.50
    expandindo
    0.49
    Portale
    0.47
    Diweddarwch
    0.47
    ագրություններ
    0.47
    DeleteBehavior
    0.46
    Act Density 0.002%

    No Known Activations