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

    Neuronpedia

    INDEX
    Explanations

    commands and instructions related to actions in gaming or programming contexts

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

    use to perform actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ----------------
    -0.35
    歼
    -0.32
     difficult
    -0.32
    unmodifiable
    -0.31
     ejus
    -0.30
    ضع
    -0.30
     more
    -0.30
    Cpp
    -0.30
    sct
    -0.30
    existe
    -0.29
    POSITIVE LOGITS
     iconLine
    0.66
    AnchorTagHelper
    0.65
     ModelExpression
    0.63
    ItemBackground
    0.63
     BoxFit
    0.63
    UnusedPrivate
    0.63
     EconPapers
    0.62
    PreInfinity
    0.62
    IVEREF
    0.59
    expandindo
    0.58
    Act Density 0.019%

    No Known Activations