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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Поль
    -0.07
    ';
↵
↵
    -0.06
    >();↵↵
    -0.06
    …)↵↵
    -0.06
    ]);
↵
↵
    -0.06
    .dataTables
    -0.06
    ?"↵↵
    -0.06
    ».↵↵
    -0.06
    .)↵↵
    -0.06
    )↵↵
    -0.06
    POSITIVE LOGITS
     anyone
    0.07
    ITS
    0.07
    .start
    0.06
    ौर
    0.06
     Carlson
    0.06
     ju
    0.06
     패
    0.06
     ○
    0.06
     Lloyd
    0.06
    ोन
    0.06
    Act Density 0.001%

    No Known Activations