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

    Neuronpedia

    INDEX
    Explanations

    toxic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     સિવ
    -0.08
    816
    -0.08
     الأمر
    -0.07
     wykon
    -0.07
     revenues
    -0.07
     имени
    -0.07
    ಿಸಲ
    -0.07
    _photo
    -0.07
    _lab
    -0.07
    PHOTO
    -0.07
    POSITIVE LOGITS
     narciss
    0.11
     interpersonal
    0.11
     abuso
    0.09
     workplaces
    0.09
     psychopath
    0.09
     Workplace
    0.08
     unhealthy
    0.08
     leadership
    0.08
     workplace
    0.08
     misog
    0.08
    Act Density 0.015%

    No Known Activations