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

    Neuronpedia

    INDEX
    Explanations

    Stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ालय
    -0.06
    /settings
    -0.06
     crawl
    -0.06
    Bin
    -0.06
     Bin
    -0.06
     SID
    -0.06
    ी।
    -0.06
    ذر
    -0.06
    ROWSER
    -0.06
    isis
    -0.06
    POSITIVE LOGITS
    uspended
    0.07
     dòng
    0.07
     даже
    0.06
     MAG
    0.06
    (nb
    0.06
     maxY
    0.06
     ẩm
    0.06
     FEATURES
    0.06
    bservable
    0.06
     Ultimate
    0.06
    Act Density 0.062%

    No Known Activations