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

    Neuronpedia

    INDEX
    Explanations

    code and numbers

    np_max-act · gemini-2.0-flash

    named entities—especially capitalized proper names, titles, places, organizations, and specific dates/numerals.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    ána
    -0.07
     aday
    -0.06
    Never
    -0.06
     pandas
    -0.06
     knit
    -0.06
    onal
    -0.06
    Markdown
    -0.06
    (rename
    -0.06
     Downs
    -0.06
    Asian
    -0.06
    POSITIVE LOGITS
     yapar
    0.06
     dataGridViewTextBoxColumn
    0.06
     zurück
    0.06
    quia
    0.06
     ultimo
    0.06
    Helpers
    0.06
     startled
    0.06
     součas
    0.06
    _Format
    0.06
    -direct
    0.06
    Act Density 0.273%

    No Known Activations