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

    Neuronpedia

    INDEX
    Explanations

    occurrences of mathematical and formatting elements in text

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

    Text within math mode environments

    np_acts-logits-general · gemini-2.0-flash

    LaTeX math and text formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.63
    ByVersion
    -0.59
    oa̍t
    -0.58
    afficheront
    -0.56
    UserScript
    -0.55
     Italijanski
    -0.55
    AutoModerator
    -0.54
     disambiguazione
    -0.53
     Administrativna
    -0.53
     Bedür
    -0.52
    POSITIVE LOGITS
    text
    0.87
    textbf
    0.57
    enumi
    0.56
    \{\\
    0.55
    operatorname
    0.55
    multicolumn
    0.53
    ValueStyle
    0.52
    Text
    0.52
    mbox
    0.50
     text
    0.49
    Act Density 0.234%

    No Known Activations