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

    Neuronpedia

    INDEX
    Explanations

    complete

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dma
    -0.07
     plasma
    -0.06
     São
    -0.06
    oreal
    -0.06
     Books
    -0.06
     dames
    -0.06
    概念
    -0.06
     Damn
    -0.06
    Born
    -0.06
    nels
    -0.06
    POSITIVE LOGITS
    Activate
    0.07
    .Wh
    0.06
     connector
    0.06
     sẵn
    0.06
     gerekmektedir
    0.06
    .volume
    0.06
    认
    0.06
    _CITY
    0.06
    .reduce
    0.06
    esor
    0.06
    Act Density 0.011%

    No Known Activations