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

    Neuronpedia

    INDEX
    Explanations

    demonstration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     সম
    -0.08
    ամ
    -0.08
    (Collider
    -0.08
    أ
    -0.07
     выплаты
    -0.07
    iversal
    -0.07
     profond
    -0.07
    াষ্ট্র
    -0.07
    χρι
    -0.07
    افته
    -0.07
    POSITIVE LOGITS
     demonstrations
    0.14
     demos
    0.12
     demonstration
    0.12
     demo
    0.12
     Demo
    0.11
     demonstra
    0.11
     Demonstr
    0.11
     demostr
    0.11
    Demo
    0.11
    demo
    0.11
    Act Density 0.026%

    No Known Activations