Multilingual LLMs dont have a clear boundary between languages. They will appear to have one since they maximize likelihoods, so asking something in English will most likely produce an English continuation, etc.
In other circumstances they might take a different path (in terms of output probability decoding) through other character sets, if the probabilities justify this.
In other circumstances they might take a different path (in terms of output probability decoding) through other character sets, if the probabilities justify this.