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

    Neuronpedia

    INDEX
    Explanations

    numpy

    np_max-act · gemini-2.0-flash

    The neuron fires on floating‐point numeric literals (decimal numbers) in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Deleted
    -0.07
    Ф
    -0.06
     Sha
    -0.06
    皮
    -0.06
     coastline
    -0.06
    _Length
    -0.06
     garden
    -0.06
    名字
    -0.06
    бас
    -0.06
    _fields
    -0.06
    POSITIVE LOGITS
     numpy
    0.08
     lush
    0.07
     conventional
    0.06
    .BorderStyle
    0.06
     lokal
    0.06
    λι
    0.06
     observers
    0.06
     karma
    0.06
     intuit
    0.06
    จน
    0.06
    Act Density 0.002%

    No Known Activations