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

    Neuronpedia

    INDEX
    Explanations

    median

    np_max-act · gemini-2.0-flash

    This neuron is essentially silent on all ordinary words and punctuation—it doesn’t respond to any of the text tokens here and so does not appear to detect any linguistic or formatting feature in these passages.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    XObject
    -0.07
     Cross
    -0.07
     startIndex
    -0.06
    _workspace
    -0.06
    有的
    -0.06
     нап
    -0.06
    "F
    -0.06
    .multipart
    -0.06
    .newLine
    -0.06
    ้าส
    -0.06
    POSITIVE LOGITS
     median
    0.12
     Median
    0.09
    median
    0.09
    dens
    0.08
    den
    0.07
     cevap
    0.07
     vaccination
    0.07
    Median
    0.07
    dik
    0.07
     styling
    0.07
    Act Density 0.003%

    No Known Activations