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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -men
    -0.07
     欧
    -0.06
     *));↵
    -0.06
     tenth
    -0.06
     quitting
    -0.06
    produ
    -0.06
    των
    -0.06
     highway
    -0.06
     );
↵
    -0.06
     glands
    -0.06
    POSITIVE LOGITS
     numbered
    0.06
    -inspired
    0.06
    _LSB
    0.06
     Durant
    0.06
    pretty
    0.06
     Lamb
    0.06
    erequisites
    0.06
     lief
    0.06
    まる
    0.06
     deutsch
    0.06
    Act Density 0.037%

    No Known Activations