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

    Neuronpedia

    INDEX
    Explanations

    Math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     реж
    -0.07
     Broadcasting
    -0.07
     출력
    -0.06
     Daw
    -0.06
    Programming
    -0.06
     persec
    -0.06
     Outdoor
    -0.06
    ycl
    -0.06
     Catherine
    -0.06
     Mast
    -0.06
    POSITIVE LOGITS
     há
    0.07
    544
    0.06
    -rate
    0.06
    (!
    0.06
    ---</
    0.06
     гри
    0.06
    (labels
    0.06
    รค
    0.06
     Дон
    0.06
     NGX
    0.06
    Act Density 0.012%

    No Known Activations