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

    Neuronpedia

    INDEX
    Explanations

    603

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Io
    -0.07
    .getRequestDispatcher
    -0.06
    Car
    -0.06
    locator
    -0.06
    dl
    -0.06
     caucus
    -0.06
    Ale
    -0.06
    (parts
    -0.06
     Flo
    -0.06
    Из
    -0.06
    POSITIVE LOGITS
     ermög
    0.06
    .NO
    0.06
     ruthless
    0.06
     "__
    0.06
     curb
    0.06
    ังกฤษ
    0.06
    ้ต
    0.06
    .А
    0.06
    ");}↵
    0.06
    だな
    0.06
    Act Density 0.020%

    No Known Activations