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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Veuillez
    -0.07
    ాయి
    -0.07
    ાયક
    -0.07
     rę
    -0.07
    .Please
    -0.07
    Donc
    -0.07
     ezért
    -0.07
                         ↵
    -0.07
     nouvelle
    -0.07
     thereby
    -0.07
    POSITIVE LOGITS
     Lastly
    0.11
     тағы
    0.11
     naman
    0.11
     lastly
    0.10
     miscellaneous
    0.10
    another
    0.10
     ebenfalls
    0.09
     또
    0.09
     మరో
    0.09
    Lastly
    0.09
    Act Density 0.378%

    No Known Activations