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

    Neuronpedia

    INDEX
    Explanations

    health and fitness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     السين
    -0.08
     cloning
    -0.08
     multicast
    -0.08
     sentidos
    -0.08
     búsqueda
    -0.08
    herlands
    -0.08
     üstün
    -0.08
     rever
    -0.08
     дополн
    -0.08
     cross
    -0.08
    POSITIVE LOGITS
     unhealthy
    0.15
     obesity
    0.14
     healthier
    0.13
     sedent
    0.13
    Calories
    0.12
     obes
    0.11
     calories
    0.11
     dietary
    0.11
     건강
    0.11
     Calories
    0.11
    Act Density 0.071%

    No Known Activations