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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    tokens that mark the start of a new text block or other special/control/schema-related markup (e.g., begin-of-text and structural/header markers).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     jenom
    -0.07
    .getHeader
    -0.06
     ولم
    -0.06
     첫
    -0.06
    六
    -0.06
     genel
    -0.06
    Chip
    -0.06
     обыч
    -0.06
    Incomplete
    -0.06
     έχει
    -0.06
    POSITIVE LOGITS
    houette
    0.07
     pours
    0.06
    logue
    0.06
    -history
    0.06
    _variables
    0.06
     listing
    0.06
    Startup
    0.06
     Ans
    0.06
     PostgreSQL
    0.06
     ®
    0.06
    Act Density 12.032%

    No Known Activations