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

    Neuronpedia

    INDEX
    Explanations

    i was thinking or going to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     сейчас
    0.47
     now
    0.47
     herein
    0.41
    Insight
    0.41
    нига
    0.41
    छ
    0.39
    जा
    0.39
     теперь
    0.39
     ഇപ്പോൾ
    0.38
     इट्स
    0.38
    POSITIVE LOGITS
     hoping
    0.98
     wondering
    0.93
     Hoping
    0.84
     aiming
    0.74
     expecting
    0.72
     intending
    0.69
     thinking
    0.68
     looking
    0.60
     meaning
    0.60
     joking
    0.60
    Act Density 0.013%

    No Known Activations