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

    Neuronpedia

    INDEX
    Explanations

    war

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resetting
    -0.08
     savings
    -0.08
    Glow
    -0.08
    合わせ
    -0.08
    香
    -0.08
     Binder
    -0.07
     sizing
    -0.07
     owning
    -0.07
     Seph
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     oorlog
    0.15
     войны
    0.14
     যুদ্ধ
    0.14
     الحرب
    0.13
     युद्ध
    0.13
     Iraq
    0.13
     savaş
    0.13
    战争
    0.13
     guerra
    0.12
     casualties
    0.12
    Act Density 0.112%

    No Known Activations