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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dex
    -0.07
    -trained
    -0.06
    .setWidth
    -0.06
    ));↵↵
    -0.06
    .reloadData
    -0.06
     encompass
    -0.06
    del
    -0.06
     :)↵↵
    -0.06
    �
    -0.06
    larından
    -0.06
    POSITIVE LOGITS
    绝望
    0.08
    钏
    0.07
    金字塔
    0.07
    墓
    0.07
    共创
    0.07
     cổ
    0.07
     WINDOW
    0.06
    끊
    0.06
    哮
    0.06
     Mile
    0.06
    Act Density 0.036%

    No Known Activations