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

    Neuronpedia

    INDEX
    Explanations

    hedonism, indulgence, and decadence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eag
    0.44
     eagles
    0.42
     अज
    0.38
    несен
    0.38
    \}$.
    0.37
     সংকোচন
    0.37
    Eagle
    0.37
    Olive
    0.36
     eagle
    0.36
     diffic
    0.36
    POSITIVE LOGITS
     decadent
    1.57
     indulgence
    1.55
     hedon
    1.55
     decad
    1.48
     indulgent
    1.45
     indul
    1.44
     indulge
    1.41
     indulging
    1.37
     immoral
    1.28
     indulged
    1.28
    Act Density 0.054%

    No Known Activations