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

    Neuronpedia

    INDEX
    Explanations

    specific names mentioned in the context of legal scenarios or criminal activities

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

    people's last names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.66
     ujednoznacz
    -0.61
    :✨
    -0.59
    KommentareTeilen
    -0.57
    expandindo
    -0.56
    izedBox
    -0.53
    BibitemShut
    -0.52
      (
    -0.52
    transQ
    -0.50
    hoeddwyd
    -0.49
    POSITIVE LOGITS
    forName
    0.36
     regalías
    0.35
    she
    0.35
    harapkan
    0.32
    ViewImports
    0.31
    The
    0.31
    HtmlAttribute
    0.31
     trekken
    0.30
     ContentValues
    0.30
    TextWatcher
    0.30
    Act Density 0.018%

    No Known Activations