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

    Neuronpedia

    INDEX
    Explanations

    dates

    np_max-act · gemini-2.0-flash

    This neuron spotlights date- and time-stamp metadata in article headers (e.g. “Updated,” month names, day numbers, year fragments, and time markers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    root
    -0.07
    imum
    -0.06
     Titan
    -0.06
     возрасте
    -0.06
     DAC
    -0.06
    _HT
    -0.06
    mall
    -0.06
    개
    -0.06
     partnering
    -0.06
    사람
    -0.06
    POSITIVE LOGITS
    $file
    0.06
     inspect
    0.06
    <File
    0.06
     сили
    0.06
     spi
    0.06
     Protective
    0.06
    蘭
    0.06
    .success
    0.06
     '..
    0.06
     separ
    0.06
    Act Density 0.011%

    No Known Activations