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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    This neuron activates on the numeric address markers (the affiliation address numbers) in academic papers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (title
    -0.06
    arer
    -0.06
     ок
    -0.06
     ATT
    -0.06
    Ein
    -0.06
     Mathematics
    -0.06
     Kata
    -0.06
     dü
    -0.06
    Authors
    -0.06
     gew
    -0.06
    POSITIVE LOGITS
     sector
    0.08
    olem
    0.07
     medically
    0.07
     orally
    0.07
    _fifo
    0.07
    displayName
    0.07
    abeled
    0.06
     sealed
    0.06
     radix
    0.06
     foundations
    0.06
    Act Density 0.000%

    No Known Activations