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

    Neuronpedia

    INDEX
    Explanations

    signal windowing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    「你
    -0.07
     floral
    -0.06
    	put
    -0.06
    cohol
    -0.06
    ""
    -0.06
     trả
    -0.06
     фах
    -0.06
    	trace
    -0.06
    िण
    -0.06
    änd
    -0.06
    POSITIVE LOGITS
     billing
    0.06
    Launcher
    0.06
    Billing
    0.06
    atively
    0.06
    ôm
    0.06
     sessiz
    0.06
    circle
    0.06
    sessions
    0.06
     salle
    0.06
    Legacy
    0.06
    Act Density 0.001%

    No Known Activations