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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     genera
    -0.07
    иля
    -0.06
    ätz
    -0.06
    win
    -0.06
    -checked
    -0.06
     lodash
    -0.06
     definitely
    -0.06
     pancre
    -0.06
    gger
    -0.06
    oci
    -0.06
    POSITIVE LOGITS
     професій
    0.07
     undercover
    0.07
    _pages
    0.06
     існу
    0.06
    Motor
    0.06
    	Route
    0.06
     Infos
    0.06
    '};↵
    0.06
     신입
    0.06
    597
    0.06
    Act Density 0.186%

    No Known Activations