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

    Neuronpedia

    INDEX
    Explanations

    exploring themes of

    np_acts-logits-general · gemini-2.5-flash-lite

    highly structured, outline/guide-style responses with headings, numbered sections, bold emphasis, and bullet-point breakdowns.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    retched
    0.46
    馋
    0.45
     QnrB
    0.44
    ᖏ
    0.43
     Tvam
    0.42
    [++
    0.42
    焲
    0.40
    рих
    0.40
    呎
    0.40
    ModelGrid
    0.39
    POSITIVE LOGITS
     lists
    0.45
     Wu
    0.45
     i
    0.44
     liste
    0.44
     how
    0.44
     Fresno
    0.43
     ste
    0.41
     todas
    0.41
     le
    0.41
     mua
    0.41
    Act Density 32.070%

    No Known Activations