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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .the
    -0.08
    :The
    -0.07
     standing
    -0.07
    _THE
    -0.06
     the
    -0.06
     IDb
    -0.06
     disparities
    -0.06
    Tel
    -0.06
    ,the
    -0.06
     pitching
    -0.06
    POSITIVE LOGITS
    학기
    0.07
    ัย
    0.07
     is
    0.07
     pokus
    0.06
    戶
    0.06
    —is
    0.06
    ์ร
    0.06
     declining
    0.06
    най
    0.06
     bipolar
    0.06
    Act Density 0.104%

    No Known Activations