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

    Neuronpedia

    INDEX
    Explanations

    names in languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    currentPage
    -0.07
     Facts
    -0.07
     ($)
    -0.07
    自治区
    -0.07
    (reverse
    -0.07
    Copyright
    -0.06
     Suppliers
    -0.06
    下乡
    -0.06
    exercise
    -0.06
    (MethodImplOptions
    -0.06
    POSITIVE LOGITS
    قف
    0.07
    摒
    0.07
    霜
    0.07
     Sasha
    0.07
     각
    0.07
     reflecting
    0.07
    ening
    0.06
     asc
    0.06
     escol
    0.06
    uplic
    0.06
    Act Density 0.087%

    No Known Activations