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

    Neuronpedia

    INDEX
    Explanations

    Locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gọn
    -0.08
     Comcast
    -0.08
     أل
    -0.07
     추천
    -0.07
    _discount
    -0.07
     backed
    -0.07
     charger
    -0.07
    ierte
    -0.07
     NVIDIA
    -0.06
     XCTAssert
    -0.06
    POSITIVE LOGITS
     Legislative
    0.06
     rel
    0.06
    øj
    0.06
         ↵↵
    0.06
    -task
    0.06
    WP
    0.06
    ıs
    0.05
     Josh
    0.05
     marital
    0.05
    [href
    0.05
    Act Density 0.047%

    No Known Activations