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

    Neuronpedia

    INDEX
    Explanations

    paragraphs with a significant amount of whitespace or formatting

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

    legal citations and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Мексичка
    -0.65
    tagHelperRunner
    -0.62
    LookAnd
    -0.55
    sizeCache
    -0.55
     ویکی‌پدی
    -0.52
     resourceCulture
    -0.52
    Билгалдахарш
    -0.47
    NameInMap
    -0.47
     Accesat
    -0.47
     cherchés
    -0.45
    POSITIVE LOGITS
     panjang
    0.44
     ciudadanía
    0.43
     réforme
    0.42
     militaires
    0.42
     lunghe
    0.42
     telefónica
    0.42
     cerimonia
    0.42
     soldadura
    0.42
    atteindre
    0.42
    navigate
    0.41
    Act Density 0.010%

    No Known Activations