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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    сов
    -0.08
    其
    -0.08
     用
    -0.07
    Davis
    -0.06
    라는
    -0.06
    τω
    -0.06
    	ns
    -0.06
    ži
    -0.06
    ث
    -0.06
    く
    -0.06
    POSITIVE LOGITS
     DataAccess
    0.07
     Autumn
    0.06
    ())↵↵↵
    0.06
    #endregion
    0.06
    endregion
    0.06
     chapter
    0.06
    !=
    0.06
    .textColor
    0.06
     newsletter
    0.06
    _ak
    0.06
    Act Density 0.010%

    No Known Activations