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

    Neuronpedia

    INDEX
    Explanations

    sleep

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    first
    -0.07
     cite
    -0.07
     showcase
    -0.07
     Force
    -0.06
    начала
    -0.06
     pursuit
    -0.06
     atlas
    -0.06
     pioneer
    -0.06
     tariff
    -0.06
     wand
    -0.06
    POSITIVE LOGITS
     sleep
    0.17
     Sleep
    0.16
    Sleep
    0.13
     sleeping
    0.12
     slept
    0.12
     sleeps
    0.11
    sleep
    0.11
     Sleeping
    0.10
    _SLEEP
    0.10
     sleepy
    0.09
    Act Density 0.012%

    No Known Activations