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
     Head
    -0.07
    umble
    -0.07
    Test
    -0.07
    MARY
    -0.07
     range
    -0.07
    ppy
    -0.07
     NET
    -0.07
     la
    -0.06
    Rotor
    -0.06
    	path
    -0.06
    POSITIVE LOGITS
    #endregion
    0.08
    典范
    0.08
     Showcase
    0.08
     artworks
    0.07
    有没有
    0.07
    עות
    0.07
     Москов
    0.07
     beverages
    0.07
    买了
    0.07
    最好不要
    0.07
    Act Density 0.000%

    No Known Activations