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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron detects XML namespace and schema declarations, especially WSDL/SOAP namespace tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (pc
    -0.06
     пут
    -0.06
     dostate
    -0.06
    rial
    -0.06
    _lat
    -0.06
    ược
    -0.06
     vyvol
    -0.06
     thirteen
    -0.06
    _follow
    -0.06
    @example
    -0.06
    POSITIVE LOGITS
    ост
    0.07
    кування
    0.07
    殖
    0.07
    Susan
    0.06
     scripture
    0.06
    Criterion
    0.06
    ，都
    0.06
     sendMessage
    0.06
     Byron
    0.06
     often
    0.06
    Act Density 0.009%

    No Known Activations