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

    Neuronpedia

    INDEX
    Explanations

    rules

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pizzas
    -0.07
     private
    -0.07
    359
    -0.06
    keit
    -0.06
     poo
    -0.06
     tenure
    -0.06
     коллек
    -0.06
    هه
    -0.06
     girls
    -0.06
    ativity
    -0.06
    POSITIVE LOGITS
    izziness
    0.07
    Potential
    0.07
    Schedule
    0.06
     thích
    0.06
    جاج
    0.06
     setTitleColor
    0.06
    ливо
    0.06
     حجم
    0.06
     ↵ ↵
    0.06
    .friend
    0.06
    Act Density 0.011%

    No Known Activations