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

    Neuronpedia

    INDEX
    Explanations

    sleep

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ación
    1.51
    ется
    1.30
    anın
    1.20
    ból
    1.11
    <0x80>
    1.09
    it
    1.03
    olok
    1.00
    owości
    0.97
    ución
    0.96
    ishes
    0.94
    POSITIVE LOGITS
     sleep
    1.35
     sleeping
    1.35
    RE
    1.29
    NG
    1.23
     sleeps
    1.18
    นอน
    1.18
     Sleeping
    1.17
    LE
    1.16
     Sleep
    1.16
     sleepers
    1.14
    Act Density 0.041%

    No Known Activations