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

    Neuronpedia

    INDEX
    Explanations

    sleep and lack thereof

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ስቃሴ
    0.50
    ุ้น
    0.36
     parity
    0.35
     photospheres
    0.35
     মুক্তিবাহিনী
    0.35
    收款
    0.34
    ंचाई
    0.34
    ধন
    0.33
    гай
    0.33
     ஏற்று
    0.33
    POSITIVE LOGITS
     sleep
    4.13
    Sleep
    3.84
     Sleep
    3.81
    sleep
    3.77
     sleeping
    3.59
    睡眠
    3.58
     sleeps
    3.42
     slept
    3.38
    睡
    3.23
    sleeping
    3.19
    Act Density 0.164%

    No Known Activations