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

    Neuronpedia

    INDEX
    Explanations

    Income statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Between
    -0.06
    	usage
    -0.06
    Uint
    -0.06
    <Self
    -0.06
    ('{}
    -0.06
    ilateral
    -0.06
     shoppers
    -0.06
     Đề
    -0.06
    -about
    -0.06
     فایل
    -0.06
    POSITIVE LOGITS
     sloppy
    0.07
     nackt
    0.07
     grips
    0.06
     glory
    0.06
    ppy
    0.06
    기
    0.06
    (worker
    0.06
     experiment
    0.06
     navigation
    0.06
     survives
    0.06
    Act Density 0.000%

    No Known Activations