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

    Neuronpedia

    INDEX
    Explanations

    input

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ễn
    -0.08
    itzer
    -0.08
     vero
    -0.07
    Undo
    -0.07
    .J
    -0.07
    먼
    -0.07
    ◇
    -0.07
     :)
    -0.07
    ڕ
    -0.07
     kê
    -0.06
    POSITIVE LOGITS
    栗
    0.08
    input
    0.07
     input
    0.07
    accumulator
    0.07
    (input
    0.07
    Specifications
    0.07
     يعمل
    0.07
     CONTROL
    0.07
    뱡
    0.07
    _working
    0.07
    Act Density 0.056%

    No Known Activations