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

    Neuronpedia

    INDEX
    Explanations

    ?>

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (_,
    -0.06
     Michigan
    -0.06
    rape
    -0.06
     naš
    -0.06
     slowly
    -0.06
     ili
    -0.06
     cabin
    -0.06
    agers
    -0.06
     speeding
    -0.06
     산업
    -0.06
    POSITIVE LOGITS
    ?>↵↵
    0.17
     brunch
    0.13
    .quit
    0.12
    ?>↵↵↵
    0.12
    ?>↵↵
    0.11
    pgsql
    0.09
     #=>
    0.08
    eguard
    0.08
    /*----------------------------------------------------------------
    0.08
    ちゃん
    0.08
    Act Density 0.002%

    No Known Activations