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

    Neuronpedia

    INDEX
    Explanations

    eating disorders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    currentItem
    0.42
    Nuestro
    0.40
    ινό
    0.40
    Когда
    0.40
    Pole
    0.39
    Order
    0.39
     গের
    0.38
     triggering
    0.38
    triggers
    0.38
     mecánico
    0.37
    POSITIVE LOGITS
     Drink
    0.57
    喝
    0.52
    drink
    0.52
     ngủ
    0.50
     drink
    0.50
     sleep
    0.50
    sleep
    0.50
    Drink
    0.49
     نیند
    0.45
    睡眠
    0.44
    Act Density 0.005%

    No Known Activations