If it's trained on Chinese data wouldn't it implicitly have a strong bias against discussing banned content?
I highly doubt that there is simply no training content about Xi Jinping, as if he didn't exist.
More-likely it is some combination of a system prompt and output-filtering code.
I more meant, if a model is only trained on 100% absolutely positive data concerning a specific subject, including any data that implies certain taboos it must avoid at all costs, the model will embed that strong bias in its learned parameters.