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

    Neuronpedia

    INDEX
    Explanations

    sections and organization within academic papers

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

    overview sections and introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.62
     propOrder
    -0.60
    adaptiveStyles
    -0.59
    tagHelperRunner
    -0.59
     EconPapers
    -0.59
     ModelExpression
    -0.59
     CanadaChoose
    -0.55
    الإنجليزية
    -0.54
    errHandler
    -0.54
    mybatisplus
    -0.52
    POSITIVE LOGITS
     introductory
    0.63
     explaining
    0.56
     wyja
    0.55
     explicou
    0.54
     explanatory
    0.54
     background
    0.52
     Erklärung
    0.51
     explain
    0.50
     clarifying
    0.50
     educate
    0.49
    Act Density 0.107%

    No Known Activations