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

    Neuronpedia

    INDEX
    Explanations

    sexual violence and gratification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     heuristic
    0.48
     payout
    0.47
     windfall
    0.47
     arbitrage
    0.47
     fiduciary
    0.46
    ዖ
    0.46
    मानी
    0.46
     사용자
    0.46
     organelles
    0.46
     workmanship
    0.45
    POSITIVE LOGITS
     Til
    0.58
     So
    0.53
     Maybe
    0.52
     Sum
    0.50
     Tal
    0.50
     E
    0.49
     Try
    0.49
     And
    0.48
     Thal
    0.48
     Ar
    0.48
    Act Density 0.000%

    No Known Activations