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

    Neuronpedia

    INDEX
    Explanations

    references to outer layers or components in various contexts

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

    outer parts or layers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eventId
    -0.66
    addContainerGap
    -0.62
    LikeLike
    -0.60
     jsonData
    -0.58
     xhr
    -0.57
     timeval
    -0.57
    charCode
    -0.57
    DataAnnotations
    -0.56
     strdup
    -0.56
     isempty
    -0.56
    POSITIVE LOGITS
     outer
    1.78
     Outer
    1.73
    Outer
    1.69
    outer
    1.63
     OUTER
    1.45
     outermost
    1.07
     inner
    0.99
     Inner
    0.96
    Inner
    0.89
    inner
    0.79
    Act Density 0.010%

    No Known Activations