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

    Neuronpedia

    INDEX
    Explanations

    sexual exploitation and violence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unethical
    0.68
     inappropriate
    0.61
     questionable
    0.61
     unsustainable
    0.57
     dubious
    0.56
     hasty
    0.55
     unhealthy
    0.54
     improper
    0.53
     misleading
    0.53
     unfair
    0.53
    POSITIVE LOGITS
     hearing
    0.82
     seeing
    0.79
    hearing
    0.77
     Hearing
    0.72
     Seeing
    0.67
    seeing
    0.66
    Hearing
    0.65
     imagining
    0.61
    Seeing
    0.61
     να
    0.61
    Act Density 0.026%

    No Known Activations