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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash

    This neuron fires most strongly on author names and citation markers (proper names of mathematicians).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    closed
    -0.07
    onces
    -0.06
    .edit
    -0.06
     elapsed
    -0.06
     eql
    -0.06
    _metric
    -0.06
    ครอง
    -0.06
    /.↵↵
    -0.06
     controls
    -0.06
    .newArrayList
    -0.06
    POSITIVE LOGITS
     customs
    0.07
    178
    0.06
     Tang
    0.06
    caffe
    0.06
     fora
    0.06
    	method
    0.06
     Diff
    0.06
    /API
    0.06
    لمه
    0.06
     Vote
    0.06
    Act Density 0.010%

    No Known Activations