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

    Neuronpedia

    INDEX
    Explanations

    expectation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     وتم
    -0.08
    -certified
    -0.08
     असून
    -0.08
    ಸ್ಯ
    -0.08
    verk
    -0.08
    fp
    -0.08
    Certified
    -0.07
     Fundamentals
    -0.07
     aangepast
    -0.07
    ukin
    -0.07
    POSITIVE LOGITS
    观察
    0.12
     beobachten
    0.12
     outcomes
    0.11
     apakah
    0.10
     Beob
    0.10
     Observe
    0.10
    结果
    0.10
     outputs
    0.09
    Observe
    0.09
    是否
    0.09
    Act Density 0.024%

    No Known Activations