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

    Neuronpedia

    INDEX
    Explanations

    numbers and measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лення
    -0.07
    Job
    -0.07
    检查
    -0.06
     ور
    -0.06
    notification
    -0.06
    onald
    -0.06
    ♥
    -0.06
    Chicago
    -0.06
     Channel
    -0.06
    TIMER
    -0.06
    POSITIVE LOGITS
     Максим
    0.07
    },"
    0.07
    orton
    0.06
     accel
    0.06
     initialValues
    0.06
    paired
    0.06
     Greenwood
    0.06
    užel
    0.06
    аров
    0.06
    ffen
    0.06
    Act Density 0.258%

    No Known Activations