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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    It detects headings, titles, or other section-start/heading tokens that mark the start of a new block or prominent label.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    惕
    -0.07
    多半
    -0.07
    .handleClick
    -0.07
    픙
    -0.07
    席
    -0.07
    توقي
    -0.06
    atrigesimal
    -0.06
     atop
    -0.06
     Swim
    -0.06
    看电影
    -0.06
    POSITIVE LOGITS
    ↵
    0.11
    ,
    0.10
    ↵
    0.10
    .,↵
    0.09
    .
↵
    0.09
    .↵
    0.09
    )
↵
    0.09
     **↵
    0.08
    #
↵
    0.08
    :↵
    0.08
    Act Density 2.991%

    No Known Activations