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

    Neuronpedia

    INDEX
    Explanations

    status updates and task management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tu
    0.46
    ICK
    0.45
    todo
    0.45
    slots
    0.42
    ль
    0.42
     рођено
    0.42
    slot
    0.42
    ánico
    0.42
    padă
    0.42
    。
    0.42
    POSITIVE LOGITS
     Statistics
    0.50
     fitness
    0.49
    Statistics
    0.47
    денциа
    0.47
     Nancy
    0.47
     Medicine
    0.46
     Fitness
    0.46
     driveway
    0.46
     guidelines
    0.45
    Physics
    0.44
    Act Density 0.001%

    No Known Activations