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

    Neuronpedia

    INDEX
    Explanations

    869

    np_max-act · gemini-2.0-flash

    The neuron specifically fires on reference and citation elements (e.g. years, volume and issue numbers, page ranges, DOIs) in scientific‐style bibliographic entries.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    rypton
    -0.07
    格
    -0.07
     天
    -0.06
    _patterns
    -0.06
    tracer
    -0.06
    .slice
    -0.06
    	free
    -0.06
     currentDate
    -0.06
     Locke
    -0.06
     spirituality
    -0.06
    POSITIVE LOGITS
    +)
    0.07
     )
    0.06
     göç
    0.06
    :_
    0.06
    ]}
    0.06
    .Syntax
    0.06
    fw
    0.06
    пп
    0.06
    DataSet
    0.06
    /create
    0.06
    Act Density 0.037%

    No Known Activations