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

    Neuronpedia

    INDEX
    Explanations

    toxicity and damage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    965
    -0.06
    grading
    -0.06
     opting
    -0.06
    CONS
    -0.06
     Sony
    -0.06
    	cursor
    -0.06
     wk
    -0.06
    agents
    -0.06
     Olympics
    -0.06
     безопасности
    -0.06
    POSITIVE LOGITS
    ligne
    0.07
    实
    0.06
    SSH
    0.06
     rencontrer
    0.06
    _iff
    0.06
     må
    0.06
    اوت
    0.06
    _rand
    0.06
     Cruiser
    0.06
    )dealloc
    0.06
    Act Density 0.056%

    No Known Activations