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

    Neuronpedia

    INDEX
    Explanations

    require

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بگ
    -0.07
     cabins
    -0.07
     shooters
    -0.06
     muž
    -0.06
     Sao
    -0.06
    的是
    -0.06
    她
    -0.06
    north
    -0.06
     Hosting
    -0.06
    ++);↵
    -0.06
    POSITIVE LOGITS
    aff
    0.07
     نقل
    0.06
    inoa
    0.06
    /ns
    0.06
    _rgba
    0.06
     watering
    0.06
    \Contracts
    0.06
     состоит
    0.06
    .Observable
    0.06
    าม
    0.06
    Act Density 0.003%

    No Known Activations