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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     egret
    -0.07
    (dl
    -0.07
     ngừng
    -0.07
     triangle
    -0.06
     Divine
    -0.06
    ился
    -0.06
    闪过
    -0.06
    تنفي
    -0.06
    _FAIL
    -0.06
    保罗
    -0.06
    POSITIVE LOGITS
    repo
    0.07
    ather
    0.06
    ʸ
    0.06
    -Christian
    0.06
    ardu
    0.06
     hdf
    0.06
    logic
    0.06
    كوم
    0.06
    滂
    0.06
    ikip
    0.06
    Act Density 0.005%

    No Known Activations