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

    Neuronpedia

    INDEX
    Explanations

    high

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     responsabilidades
    -0.08
                    ↵↵
    -0.08
            ↵↵
    -0.07
     Shade
    -0.07
     departments
    -0.07
    Department
    -0.07
     Starter
    -0.07
    selected
    -0.07
    department
    -0.07
                ↵↵
    -0.07
    POSITIVE LOGITS
    ুগ
    0.09
     похуд
    0.09
    走势
    0.09
     ઉત્પાદન
    0.08
     nový
    0.08
     üret
    0.08
     makam
    0.08
    (price
    0.08
     повышение
    0.08
     ઊ
    0.08
    Act Density 0.001%

    No Known Activations