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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    How
    -0.07
    ј
    -0.07
    ")]↵↵
    -0.07
     Друг
    -0.06
    bery
    -0.06
    –
    -0.06
     fighter
    -0.06
     acos
    -0.06
    xy
    -0.06
    Back
    -0.06
    POSITIVE LOGITS
     Dickinson
    0.08
     U
    0.07
     Paula
    0.07
     pg
    0.07
     Seks
    0.07
    ().↵
    0.06
     PV
    0.06
     u
    0.06
    美國
    0.06
     زیبا
    0.06
    Act Density 0.027%

    No Known Activations