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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical values

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

    json code snippets and structural elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.91
    httphttps
    -0.75
    rungsseite
    -0.70
    ValueStyle
    -0.70
     кӀ
    -0.62
    Aiheesta
    -0.60
    UrlResolution
    -0.60
    awtextra
    -0.60
     ostavi
    -0.57
    Manbalar
    -0.56
    POSITIVE LOGITS
    SuspendLayout
    0.53
    StructEnd
    0.41
    MessageOf
    0.40
    /***/
    0.40
    Diwedd
    0.32
    ⤹
    0.32
     CanadaChoose
    0.32
    OrEqual
    0.31
    تقاوى
    0.30
    adaptiveStyles
    0.29
    Act Density 0.042%

    No Known Activations