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

    Neuronpedia

    INDEX
    Explanations

    mathematical or statistical functions and their properties

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

    True/False questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.57
     للاسماء
    -0.52
     تضيفلها
    -0.50
    Hentet
    -0.44
     ModelExpression
    -0.44
    новниш
    -0.43
    rungsseite
    -0.43
    webElementXpaths
    -0.43
    gdala
    -0.42
    IUrlHelper
    -0.42
    POSITIVE LOGITS
    Conseils
    0.48
     gruesa
    0.47
    Vidéo
    0.46
    instrumental
    0.45
    baliknya
    0.45
     Wirklichkeit
    0.43
     ingenieros
    0.43
     Summe
    0.42
     rústica
    0.42
     delgada
    0.42
    Act Density 1.304%

    No Known Activations