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

    Neuronpedia

    INDEX
    Explanations

    references to specific shows or media content

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

    legal and descriptive phrasing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.98
     виправивши
    -0.72
     propOrder
    -0.67
    oredCriteria
    -0.65
    principalTable
    -0.65
    帖最后由
    -0.61
    出版年
    -0.57
     ब्रेकडाउन
    -0.56
    hamshire
    -0.55
    DeleteBehavior
    -0.55
    POSITIVE LOGITS
    csname
    0.36
    ʖ
    0.36
     abzu
    0.35
    <?
    0.35
    BufferException
    0.35
     toothbrush
    0.35
     toothed
    0.35
     alone
    0.35
    canestro
    0.35
    newVal
    0.35
    Act Density 0.157%

    No Known Activations