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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arrison
    -0.07
    我认为
    -0.07
    snake
    -0.06
     warrior
    -0.06
     networks
    -0.06
    uddenly
    -0.06
     ציבור
    -0.06
    𝒄
    -0.06
    rocket
    -0.06
    death
    -0.06
    POSITIVE LOGITS
    .FindElement
    0.07
    .addHandler
    0.07
    .getY
    0.07
    NonQuery
    0.07
    allel
    0.07
    合力
    0.07
    .ItemsSource
    0.06
     Yıl
    0.06
     같이
    0.06
     הצליח
    0.06
    Act Density 0.001%

    No Known Activations