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

    Neuronpedia

    INDEX
    Explanations

    ural

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CLEAN
    -0.08
     coming
    -0.07
     charges
    -0.07
    -wheel
    -0.07
    ewan
    -0.07
    Race
    -0.06
     DF
    -0.06
     SIMPLE
    -0.06
    Tim
    -0.06
     enforcement
    -0.06
    POSITIVE LOGITS
    igner
    0.07
     dcc
    0.07
    ?>↵↵↵
    0.07
    lendir
    0.07
     ucz
    0.07
    ($.
    0.07
     зі
    0.07
    .mar
    0.07
    _mE
    0.06
     ساله
    0.06
    Act Density 0.018%

    No Known Activations