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

    Neuronpedia

    INDEX
    Explanations

    Car maintenance/service

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     root
    -0.07
     Би
    -0.07
    卢
    -0.07
    =edge
    -0.07
    	points
    -0.07
    界
    -0.06
    noise
    -0.06
    _WIFI
    -0.06
    を開
    -0.06
     أنها
    -0.06
    POSITIVE LOGITS
    Strength
    0.07
    qualified
    0.07
     tallest
    0.06
    
    0.06
     rok
    0.06
    [r
    0.06
    551
    0.06
     Shoot
    0.06
    ोध
    0.06
    踏
    0.06
    Act Density 0.016%

    No Known Activations