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

    Neuronpedia

    INDEX
    Explanations

    Stuart and Julien names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Batter
    -0.08
     ตำ
    -0.08
    ázd
    -0.07
    348
    -0.07
    498
    -0.07
    言わ
    -0.07
     /=
    -0.07
     rice
    -0.07
    .*
    -0.06
     iParam
    -0.06
    POSITIVE LOGITS
     Marshall
    0.08
     Meredith
    0.08
    -production
    0.07
    <!--
    0.07
     Megan
    0.07
     Andrew
    0.07
     Brid
    0.07
     Мар
    0.07
    _finish
    0.07
    ----↵↵
    0.07
    Act Density 0.088%

    No Known Activations