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

    Neuronpedia

    INDEX
    Explanations

    structure or format markers in documents

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

    HTML table-related tokens

    np_acts-logits-general · gemini-2.0-flash

    basic divisor of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.59
    ]")]
    -0.58
     Extragalactic
    -0.56
    ırken
    -0.53
    reszcie
    -0.53
     dapatkan
    -0.53
    newValue
    -0.52
    antaranya
    -0.52
    Dziękuję
    -0.52
    ABUL
    -0.49
    POSITIVE LOGITS
    <tbody>
    1.03
    <table>
    1.02
    </td>
    0.76
    <thead>
    0.75
     colspan
    0.72
    </table>
    0.69
    </th>
    0.67
     يتيمه
    0.66
    findpost
    0.65
    OGND
    0.65
    Act Density 0.043%

    No Known Activations