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

    Neuronpedia

    INDEX
    Explanations

    time (hours/minutes)

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of elapsed time intervals, e.g. phrases like “half an hour later,” “hours after,” or “minutes.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     spinning
    -0.07
     larvae
    -0.06
    aic
    -0.06
    닥
    -0.06
    شن
    -0.06
     swollen
    -0.06
    awks
    -0.06
    _mobile
    -0.06
    empo
    -0.06
    Index
    -0.06
    POSITIVE LOGITS
     التش
    0.07
     firefighters
    0.07
     абсолют
    0.07
     sts
    0.07
     hrs
    0.07
     исключ
    0.07
     AssemblyProduct
    0.07
     intéress
    0.06
    制造
    0.06
     zvlá
    0.06
    Act Density 0.022%

    No Known Activations