Umm, you might want to read my article then where it talks about how it shouldn't mention military casualties and stuff. It VERY much is self-aware of what it's doing and actively suppressing information. It's a bit creepy, actually! (Skip to Step 4 in the article):

https://reedmayhew.medium.com/deepseek-r1-how-an-ai-exposed-its-own-censorship-and-manipulation-edb2c7f8e2cf