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

    Neuronpedia

    INDEX
    Explanations

    reviews and statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	InputStream
    -0.07
     sund
    -0.07
    iere
    -0.07
     BITS
    -0.07
    ri
    -0.07
    _over
    -0.06
     їм
    -0.06
        
    -0.06
    ala
    -0.06
     surrounds
    -0.06
    POSITIVE LOGITS
     호텔
    0.07
    Fixture
    0.06
     hydration
    0.06
     منها
    0.06
     CONT
    0.06
     mongo
    0.06
    基础
    0.06
     demographics
    0.06
    exclusive
    0.06
     */↵↵↵
    0.06
    Act Density 0.019%

    No Known Activations