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

    Neuronpedia

    INDEX
    Explanations

    system

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     of
    -0.09
    shuffle
    -0.08
    ([...
    -0.07
    ://
    -0.07
    捐赠
    -0.07
    eno
    -0.07
    /tasks
    -0.07
    [R
    -0.07
     TWO
    -0.07
    _atual
    -0.07
    POSITIVE LOGITS
     Systems
    0.09
     systems
    0.08
    	System
    0.08
     system
    0.08
     своем
    0.08
    系统
    0.08
     "','"
    0.07
    沛
    0.07
     SYSTEM
    0.07
    getID
    0.07
    Act Density 0.144%

    No Known Activations