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

    Neuronpedia

    INDEX
    Explanations

    sleep and its consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    école
    0.96
     trips
    0.94
     Кре
    0.92
     Pirates
    0.87
     ચો
    0.87
     Pb
    0.86
    vist
    0.86
    ель
    0.85
     Jehovah
    0.85
    ߋ
    0.84
    POSITIVE LOGITS
     deprivation
    1.23
     apnea
    1.21
    inducing
    1.08
    কাত
    1.00
    火山
    0.99
     woll
    0.96
    yd
    0.96
     deprived
    0.94
    walkers
    0.92
    俭
    0.92
    Act Density 0.039%

    No Known Activations