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

    Neuronpedia

    INDEX
    Explanations

    access

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _LINUX
    -0.07
     UFO
    -0.06
    INGTON
    -0.06
    Кон
    -0.06
    рования
    -0.06
     MK
    -0.06
    ček
    -0.06
     counseling
    -0.06
    	password
    -0.06
    _fault
    -0.06
    POSITIVE LOGITS
    чень
    0.06
    Inc
    0.06
     removeFrom
    0.06
    іла
    0.06
    .super
    0.06
    .documentElement
    0.06
     سیستم
    0.06
     shuts
    0.06
     �
    0.06
     laut
    0.06
    Act Density 0.014%

    No Known Activations