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

    Neuronpedia

    INDEX
    Explanations

    sleep duration and hours

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    レンジ
    0.81
     quick
    0.78
     steering
    0.76
    ତା
    0.73
     quickly
    0.72
     مذہ
    0.70
    Gate
    0.69
     speedy
    0.69
    ेडियम
    0.69
     backsplash
    0.69
    POSITIVE LOGITS
     Sleep
    1.45
     sleep
    1.37
    Sleep
    1.36
    睡眠
    1.26
    sleep
    1.18
     Sleeping
    1.13
     slept
    1.06
    Sleeping
    1.03
     sleeping
    1.00
     Schlaf
    0.99
    Act Density 0.229%

    No Known Activations