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

    Neuronpedia

    INDEX
    Explanations

    */

    np_max-act · gemini-2.0-flash

    The neuron fires on the boundary right after a block‐comment header (e.g. the closing `*/` following a license comment), marking the transition from the initial comment into the actual code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     qos
    -0.07
     regulatory
    -0.06
     अप
    -0.06
    ability
    -0.06
    	memset
    -0.06
    libs
    -0.06
     PureComponent
    -0.06
    _FLUSH
    -0.06
    ial
    -0.06
    Holy
    -0.06
    POSITIVE LOGITS
     provoke
    0.09
     حسین
    0.07
     participating
    0.07
    oq
    0.06
     acompan
    0.06
    942
    0.06
    ahoma
    0.06
    .dateTime
    0.06
     Court
    0.06
     гориз
    0.06
    Act Density 0.002%

    No Known Activations