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

    Neuronpedia

    INDEX
    Explanations

    exponents and simplification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     imperialism
    -0.07
     vér
    -0.06
     حساب
    -0.06
    сам
    -0.06
    Công
    -0.06
    徒
    -0.06
    .Hand
    -0.06
    .analysis
    -0.06
     میدان
    -0.06
    ETweet
    -0.06
    POSITIVE LOGITS
    (newState
    0.06
     bc
    0.06
    sizes
    0.06
     OCC
    0.06
     Deleting
    0.06
     neighborhoods
    0.06
    (mask
    0.06
    某
    0.06
    ูตร
    0.06
    ITEM
    0.06
    Act Density 0.005%

    No Known Activations