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

    Neuronpedia

    INDEX
    Explanations

    scientific publications

    np_max-act · gemini-2.0-flash

    The neuron is tuned to pick out numeric tokens that denote citation details (e.g. journal volume and page numbers) in the reference sections.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Ice
    -0.08
     sleep
    -0.08
     Water
    -0.08
     footh
    -0.07
     occurred
    -0.07
     paper
    -0.07
     Sept
    -0.07
     oc
    -0.07
     trẻ
    -0.07
     مه
    -0.07
    POSITIVE LOGITS
    465
    0.09
    567
    0.08
    463
    0.08
    165
    0.08
    464
    0.08
    263
    0.08
    269
    0.08
    762
    0.08
    861
    0.07
    765
    0.07
    Act Density 0.150%

    No Known Activations