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

    Neuronpedia

    INDEX
    Explanations

    angular

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cata
    -0.08
    Cast
    -0.07
     hoax
    -0.07
     extension
    -0.07
     bread
    -0.06
     dread
    -0.06
    目录
    -0.06
     speaker
    -0.06
     який
    -0.06
     Budget
    -0.06
    POSITIVE LOGITS
    \Twig
    0.07
     [|
    0.07
     anz
    0.06
     accomp
    0.06
     erklä
    0.06
     bedrooms
    0.06
    İng
    0.06
    ыл
    0.06
    فع
    0.06
    kle
    0.06
    Act Density 0.483%

    No Known Activations