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

    Neuronpedia

    INDEX
    Explanations

    elements related to structured data or tables in documents

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

    Preceding special characters or punctuation

    np_acts-logits-general · gemini-2.0-flash

    data reporting contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .";
    -0.72
    !';
    -0.67
    _'.$
    -0.66
    .';
    -0.64
    $.
    -0.64
    .'”
    -0.63
    NUMX
    -0.61
    ."));
    -0.60
    ."),
    -0.60
    >--}}
    -0.59
    POSITIVE LOGITS
    </th>
    0.94
     (%)
    0.92
     للاسماء
    0.78
    NameInMap
    0.78
    (%)
    0.75
    GEBURTSDATUM
    0.73
    (\%)
    0.72
    ($)
    0.72
    adaptiveStyles
    0.72
     (°
    0.70
    Act Density 0.566%

    No Known Activations