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

    Neuronpedia

    INDEX
    Explanations

    concepts and vocabulary associated with actions and classifications

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

    states followed by specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yntaxException
    -0.47
     صوتيه
    -0.45
    rawDesc
    -0.44
     незавершена
    -0.41
    RenderAtEndOf
    -0.40
     Paglinawan
    -0.39
    AndEndTag
    -0.39
    CppMethod
    -0.38
    -------------</
    -0.38
     للمعارف
    -0.38
    POSITIVE LOGITS
     intimacy
    0.53
     кӀ
    0.48
     provocation
    0.48
     Calder
    0.48
     compromised
    0.48
    timacy
    0.48
     كورة
    0.47
     Gough
    0.47
     abstracted
    0.47
     Iterate
    0.47
    Act Density 0.006%

    No Known Activations