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

    Neuronpedia

    INDEX
    Explanations

    Russia, Ukraine, war, Soviet, Russian names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ist
    1.66
     związ
    1.55
    ется
    1.53
    ет
    1.48
    নি
    1.46
    izes
    1.46
     dotyczą
    1.46
    heet
    1.43
    achte
    1.43
    ltr
    1.41
    POSITIVE LOGITS
    ب
    1.64
    Гра
    1.63
    Russia
    1.60
     روسی
    1.55
     Medvedev
    1.54
    Ukrainian
    1.52
    س
    1.45
    Russian
    1.43
    Ivan
    1.42
     Г
    1.41
    Act Density 0.104%

    No Known Activations