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

    Neuronpedia

    INDEX
    Explanations

    debugging code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    šak
    -0.08
     čt
    -0.07
    .Tests
    -0.07
    ाध
    -0.06
    )");↵↵
    -0.06
     rağmen
    -0.06
    爷
    -0.06
    زيز
    -0.06
    김
    -0.06
    ![↵
    -0.06
    POSITIVE LOGITS
     RPM
    0.07
    Minus
    0.06
     eman
    0.06
    eof
    0.06
     talents
    0.06
     big
    0.06
     Georgia
    0.06
    Charles
    0.06
     dirs
    0.06
     forb
    0.06
    Act Density 0.018%

    No Known Activations