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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their associated identifiers in data structures

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

    Code or data fragments

    np_acts-logits-general · gemini-2.0-flash

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -1.09
     beginnetje
    -0.77
     Shakspeare
    -0.72
     Monfieur
    -0.71
     Efq
    -0.69
     chofe
    -0.68
    mybatisplus
    -0.68
     dentaire
    -0.68
    Portail
    -0.67
    setof
    -0.66
    POSITIVE LOGITS
    </i>
    0.62
    <unused61>
    0.54
    ↵↵
    0.54
    </blockquote>
    0.53
    <unused60>
    0.52
    </code>
    0.52
    <unused62>
    0.50
     */
    0.50
    <unused63>
    0.50
    ↵
    0.49
    Act Density 0.503%

    No Known Activations