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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and organizations

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

    names ending in 'er' or 'ne'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CrossRef
    -0.39
     상세
    -0.38
     الحره
    -0.36
    hamdulillah
    -0.36
    IActionResult
    -0.36
    transQ
    -0.36
    selaer
    -0.36
     reborn
    -0.36
     للمعارف
    -0.35
    seido
    -0.34
    POSITIVE LOGITS
    hoeddwyd
    0.56
     EnglishChoose
    0.55
     ویکی‌پدی
    0.54
    MessageOf
    0.54
    EndGlobalSection
    0.54
    Geplaatst
    0.53
    RefNanny
    0.52
    OGND
    0.52
     يتيمه
    0.51
    parsedMessage
    0.51
    Act Density 0.015%

    No Known Activations