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

    Neuronpedia

    INDEX
    Explanations

    monetary policy, heavily relates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    end
    1.30
    etl
    1.25
    </h3>
    1.22
    </h2>
    1.15
    et
    1.13
    ד
    1.13
    up
    1.12
    itt
    1.11
    age
    1.10
    üm
    1.09
    POSITIVE LOGITS
    ع
    1.61
    า
    1.43
    ی
    1.39
     Каждый
    1.29
    علم
    1.22
     Высо
    1.16
     ใจ
    1.16
    ה
    1.15
     Ủy
    1.13
    ты
    1.12
    Act Density 0.250%

    No Known Activations