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

    Neuronpedia

    INDEX
    Explanations

    Additional context/information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accurate
    -0.07
     wholesale
    -0.06
     contradictory
    -0.06
     lượng
    -0.06
    /form
    -0.06
    幼
    -0.06
    (':
    -0.06
    ути
    -0.06
     Ent
    -0.06
     URI
    -0.06
    POSITIVE LOGITS
     Luxury
    0.07
    يف
    0.07
     VALUES
    0.07
    ------+------+
    0.06
    ابة
    0.06
     віднос
    0.06
     Officer
    0.06
     bigotry
    0.06
     sucht
    0.06
    _DO
    0.06
    Act Density 0.155%

    No Known Activations