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

    Neuronpedia

    INDEX
    Explanations

    references to time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     porta
    -0.06
     Lone
    -0.06
    SOLE
    -0.06
     якого
    -0.06
     TSA
    -0.06
     ГО
    -0.06
    =-=-
    -0.06
     sharp
    -0.06
     Manny
    -0.06
     med
    -0.06
    POSITIVE LOGITS
     caution
    0.07
    Calling
    0.06
    將
    0.06
     hypothesis
    0.06
    ＿
    0.06
    encoder
    0.06
    /int
    0.06
    .websocket
    0.06
    ako
    0.06
     příro
    0.06
    Act Density 0.031%

    No Known Activations