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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and special characters in the text

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

    Numbers or symbols followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    code and structured text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.90
    WireFormatLite
    -0.85
     utafitiHapana
    -0.77
     Савезне
    -0.74
     виправивши
    -0.74
    TagHelper
    -0.72
    oredCriteria
    -0.71
     <",
    -0.71
    цездатний
    -0.71
    TagMode
    -0.70
    POSITIVE LOGITS
    <eos>
    0.79
     للاسماء
    0.59
    </u>
    0.57
    </code>
    0.57
    .}}
    0.50
    Hentet
    0.48
     M
    0.48
    </b>
    0.48
    </th>
    0.47
    </h2>
    0.47
    Act Density 0.202%

    No Known Activations