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

    Neuronpedia

    INDEX
    Explanations

    consequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     volts
    -0.08
     anarch
    -0.08
     Ip
    -0.07
    出
    -0.07
     antics
    -0.07
     bal
    -0.07
    (vol
    -0.07
     vý
    -0.07
     حجم
    -0.07
     phe
    -0.07
    POSITIVE LOGITS
     долгов
    0.13
     langfrist
    0.13
     мерз
    0.11
    长期
    0.11
     dauerhaft
    0.11
     étern
    0.11
     طويلة
    0.11
     dài
    0.11
     দীর্ঘ
    0.11
     indefinitely
    0.10
    Act Density 0.230%

    No Known Activations