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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ُ
    -0.07
    乱象
    -0.06
     Dropdown
    -0.06
    Allen
    -0.06
    選
    -0.06
     baptized
    -0.06
    桑
    -0.06
    ستخدم
    -0.06
    ив
    -0.06
    教えて
    -0.06
    POSITIVE LOGITS
     TIFF
    0.08
     wxDefault
    0.07
     knitting
    0.07
    .startActivity
    0.07
    ◑
    0.07
    kernel
    0.07
    _cores
    0.07
     heap
    0.07
    monthly
    0.07
    _sqrt
    0.07
    Act Density 0.024%

    No Known Activations