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

    Neuronpedia

    INDEX
    Explanations

    @{

    np_max-act · gemini-2.0-flash

    This neuron fires on the tokens used in code‐header comment blocks—especially documentation and licensing markers like “/**”, “@…”, “addtogroup”, and related structured‐comment tags.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     crossings
    -0.07
    .ID
    -0.07
     Median
    -0.07
     DATA
    -0.06
     day
    -0.06
    iyordu
    -0.06
    descending
    -0.06
     years
    -0.06
     Day
    -0.06
     spot
    -0.06
    POSITIVE LOGITS
     monoc
    0.06
     @{↵
    0.06
    reetings
    0.06
    (Map
    0.06
     strokes
    0.06
    �
    0.06
    ко
    0.06
    (adj
    0.06
    //$
    0.06
                        ↵
    0.06
    Act Density 0.000%

    No Known Activations