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

    Neuronpedia

    INDEX
    Explanations

    identifiers, codes, and numerical representations related to content and classes

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

    user input followed by specific token

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enfans
    -0.34
     communautaire
    -0.32
     democracia
    -0.31
    Kontrola
    -0.30
     fy
    -0.30
     éprou
    -0.30
     sportifs
    -0.29
     sortant
    -0.29
     démocr
    -0.29
     rév
    -0.28
    POSITIVE LOGITS
    :✨
    0.80
     noDo
    0.69
     المعيارى
    0.65
    contentLoaded
    0.58
    NameInMap
    0.57
     surla
    0.56
    SharedCtor
    0.56
     EconPapers
    0.55
     ExecuteAsync
    0.55
     CanadaChoose
    0.54
    Act Density 0.000%

    No Known Activations