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

    Neuronpedia

    INDEX
    Explanations

    empires, colonialism, and wars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المستخدم
    0.38
     czynności
    0.35
     tabella
    0.35
     ব্যবহারের
    0.34
     الماء
    0.34
     keepsake
    0.33
    秘书
    0.33
     használ
    0.32
     texted
    0.31
     inkjet
    0.30
    POSITIVE LOGITS
     guerras
    0.59
     colonialism
    0.53
     empires
    0.51
     imperialism
    0.50
     colonial
    0.49
     invasions
    0.49
     conquests
    0.47
     nationalism
    0.47
     সাম্রাজ
    0.47
     totalitarian
    0.47
    Act Density 0.327%

    No Known Activations