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

    Neuronpedia

    INDEX
    Explanations

    titled/entitled

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     combin
    -0.07
     anchor
    -0.07
    -blog
    -0.07
     assistance
    -0.06
    /compiler
    -0.06
    .expected
    -0.06
    /her
    -0.06
     dataSet
    -0.06
     true
    -0.06
     lore
    -0.06
    POSITIVE LOGITS
     titled
    0.08
     entitled
    0.07
    ังน
    0.07
    нят
    0.07
    Turning
    0.07
    Point
    0.07
    erten
    0.07
     diyor
    0.06
    judul
    0.06
    EFF
    0.06
    Act Density 0.010%

    No Known Activations