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

    Neuronpedia

    INDEX
    Explanations

    specific pronouns and personal identifiers in the text

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

    Yousafzai or Moroi names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.52
    basicConfig
    -0.50
    AndEndTag
    -0.49
    richTextPanel
    -0.47
     Autorisations
    -0.47
     snippetHide
    -0.47
     maș
    -0.47
    تقاوى
    -0.47
    FromNib
    -0.46
    TagNumber
    -0.46
    POSITIVE LOGITS
    lei
    1.28
    lai
    1.24
    tei
    1.17
    dei
    1.15
    rai
    1.15
    Lai
    1.14
    sei
    1.12
    cai
    1.12
     Lai
    1.12
    ei
    1.11
    Act Density 0.023%

    No Known Activations