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

    Neuronpedia

    INDEX
    Explanations

    Crimean Tatar and Uyghur conflicts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     doctorate
    0.43
    izzando
    0.41
     doct
    0.38
     言っ
    0.38
    博士
    0.38
     डॉक्ट
    0.37
     доктор
    0.36
     obsess
    0.36
     trib
    0.36
    พิเศษ
    0.35
    POSITIVE LOGITS
    माइ
    0.42
    తంగా
    0.38
    Tatar
    0.38
    Ani
    0.37
    ifa
    0.36
    ҕ
    0.36
    Soft
    0.36
     Tatar
    0.35
     Conquer
    0.35
    umes
    0.35
    Act Density 0.003%

    No Known Activations