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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     surgeries
    -0.06
    대비
    -0.06
     dois
    -0.06
     Lịch
    -0.06
    워
    -0.06
    	type
    -0.06
     kvůli
    -0.06
    IconModule
    -0.06
    waukee
    -0.05
    addons
    -0.05
    POSITIVE LOGITS
    ing
    0.07
    《
    0.07
    При
    0.07
     ($_
    0.06
     Tart
    0.06
     Assembly
    0.06
    \D
    0.06
    Dev
    0.06
     Ads
    0.06
    企
    0.06
    Act Density 0.018%

    No Known Activations