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

    Neuronpedia

    INDEX
    Explanations

    comment termination syntax in code

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

    Code comments or code-related syntax

    np_acts-logits-general · gemini-2.0-flash

    closing comment markers or section delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gran
    -0.61
     fod
    -0.56
     Paglinawan
    -0.56
    leh
    -0.52
     Brid
    -0.52
    mond
    -0.51
    brid
    -0.51
    stretchr
    -0.50
     Gran
    -0.50
     grand
    -0.50
    POSITIVE LOGITS
    findpost
    1.08
    KommentareTeilen
    0.98
    __*/
    0.94
     الحره
    0.92
     wireType
    0.90
     */
    0.87
     */}
    0.86
    .*")]
    0.86
    httphttps
    0.86
    ]")]
    0.84
    Act Density 0.122%

    No Known Activations