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

    Neuronpedia

    INDEX
    Explanations

    leave

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enge
    -0.06
     постоянно
    -0.06
    zet
    -0.06
     sorts
    -0.06
    .access
    -0.06
    engo
    -0.06
    o
    -0.06
    회
    -0.06
    middleware
    -0.06
    barang
    -0.06
    POSITIVE LOGITS
    建议
    0.07
     CAD
    0.06
     gestures
    0.06
    izar
    0.06
     recommendation
    0.06
    (series
    0.06
    圭圭
    0.06
     پیشنه
    0.06
    ().'/
    0.06
     recommending
    0.06
    Act Density 0.001%

    No Known Activations