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

    Neuronpedia

    INDEX
    Explanations

    tiredness, boredom, exhaustion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unknowingly
    0.82
     thoại
    0.80
     unwittingly
    0.79
     unexpected
    0.76
    ຕິດຕໍ່
    0.76
     اعز
    0.76
    unexpected
    0.74
     unexpectedly
    0.73
    kości
    0.71
     عجیب
    0.71
    POSITIVE LOGITS
     tired
    2.41
    tired
    2.05
     Tired
    2.01
     fatigue
    1.94
     fatigued
    1.84
     bored
    1.77
     exhausted
    1.73
     weary
    1.71
     boredom
    1.70
     tiredness
    1.69
    Act Density 0.191%

    No Known Activations