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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinions or emphatic statements

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

    words starting phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.77
     ویکی‌پدی
    -0.76
    AddTagHelper
    -0.72
    uxxxx
    -0.71
    libft
    -0.64
     Biôgrafia
    -0.61
    OGND
    -0.60
    -0.60
    Билгалдахарш
    -0.59
     cherchés
    -0.58
    POSITIVE LOGITS
    tagHelperRunner
    0.47
     Worth
    0.30
     оригіналу
    0.29
    Defaults
    0.28
    wärts
    0.28
    /***/
    0.28
    bootstrapcdn
    0.27
    为止
    0.27
    艋
    0.26
     Lo
    0.26
    Act Density 0.004%

    No Known Activations