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

    Neuronpedia

    INDEX
    Explanations

    arithmetic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     springfox
    -0.08
     Refugee
    -0.07
    _inline
    -0.07
    を超え
    -0.07
    癯
    -0.07
    悯
    -0.07
    Render
    -0.06
    (ray
    -0.06
    hé
    -0.06
    ray
    -0.06
    POSITIVE LOGITS
     like
    0.07
    >>();↵↵
    0.07
     ();
↵
    0.07
     ";
↵
    0.07
    ⋯
    0.07
    地点
    0.07
    씹
    0.07
    我说
    0.07
     ";↵
    0.07
    ism
    0.07
    Act Density 0.002%

    No Known Activations