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

    Neuronpedia

    INDEX
    Explanations

    surgical procedures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Iterate
    -0.07
    osten
    -0.07
    -add
    -0.07
    該
    -0.06
    (IP
    -0.06
    .one
    -0.06
    roker
    -0.06
    Station
    -0.06
    	ip
    -0.06
    ,password
    -0.06
    POSITIVE LOGITS
    lemen
    0.08
    _GB
    0.07
     intervening
    0.07
     STRICT
    0.07
    ійного
    0.07
     "><
    0.06
    Doug
    0.06
    FORCE
    0.06
    -operative
    0.06
    	REQUIRE
    0.06
    Act Density 0.046%

    No Known Activations