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

    Neuronpedia

    INDEX
    Explanations

    editing existing text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ITER
    -0.07
     spanning
    -0.07
     grayscale
    -0.07
    大奖
    -0.06
     uppercase
    -0.06
    ༚
    -0.06
     Centers
    -0.06
    (dtype
    -0.06
     umbrella
    -0.06
    RootElement
    -0.06
    POSITIVE LOGITS
     orders
    0.07
     Kısa
    0.07
    吃得
    0.07
     לוקח
    0.06
    .)
    0.06
    iking
    0.06
     fucking
    0.06
    먹
    0.06
    Ǐ
    0.06
     الو
    0.06
    Act Density 0.005%

    No Known Activations