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

    Neuronpedia

    INDEX
    Explanations

    code structure elements such as function calls, closures, and brackets

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

    Code syntax: parentheses and semicolons

    np_acts-logits-general · gemini-2.0-flash

    closing code blocks and strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.78
     Diony
    -0.57
    adpleegd
    -0.57
    fromCharCode
    -0.56
    LLocation
    -0.53
    SourceChecksum
    -0.53
    corer
    -0.51
     שוליים
    -0.51
    érience
    -0.51
    hésite
    -0.49
    POSITIVE LOGITS
     */
    1.57
    */
    1.48
    "));
    1.43
    '),
    1.30
    "))
    1.29
    ")]
    1.28
    </code>
    1.28
    ");
    1.27
    "),
    1.27
    </blockquote>
    1.27
    Act Density 0.819%

    No Known Activations