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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash

    The neuron activates on temporal schedule phrases—mentions of regular time intervals (e.g. “every 3 months,” “once every five years,” “at 2-week intervals,” “every hour,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    iola
    -0.07
     seek
    -0.06
     أعلام
    -0.06
    talk
    -0.06
     swamp
    -0.06
    .close
    -0.06
    Flight
    -0.06
    教育
    -0.06
    #+
    -0.06
    (player
    -0.06
    POSITIVE LOGITS
     whispered
    0.08
     Hemp
    0.06
     intimidating
    0.06
    Volt
    0.06
    _decimal
    0.06
     glossy
    0.06
    <_
    0.06
    úng
    0.06
    URT
    0.06
    dol
    0.06
    Act Density 0.012%

    No Known Activations