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

    Neuronpedia

    INDEX
    Explanations

    punctuation or separators in text, especially commas and braces

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

    Preceding a number or function

    np_acts-logits-general · gemini-2.0-flash

    punctuation and common words like is, that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.69
     فريبيس
    -0.68
     noDo
    -0.66
    bootstrapcdn
    -0.66
     يتيمه
    -0.65
    ChildScrollView
    -0.60
    :✨
    -0.58
     AssemblyVersion
    -0.57
    xase
    -0.56
     ModelExpression
    -0.56
    POSITIVE LOGITS
     that
    0.65
     were
    0.65
     is
    0.60
    ,$_
    0.58
     while
    0.58
     وسلم
    0.57
     morire
    0.55
     in
    0.55
     alike
    0.54
     until
    0.54
    Act Density 0.393%

    No Known Activations