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

    Neuronpedia

    INDEX
    Explanations

    references to data and text formats or types

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

    text and labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.89
    TagMode
    -0.79
     يتيمه
    -0.74
     CreateTagHelper
    -0.72
     propOrder
    -0.68
    AndEndTag
    -0.67
    EndGlobalSection
    -0.66
     الرياضيه
    -0.66
    DoubleQuotes
    -0.66
     transférez
    -0.63
    POSITIVE LOGITS
    text
    0.53
     text
    0.52
    TextNode
    0.43
    Text
    0.41
     texte
    0.40
     texto
    0.39
     тек
    0.39
    Content
    0.39
     текст
    0.39
     текста
    0.39
    Act Density 0.002%

    No Known Activations