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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     elm
    -0.06
     enquanto
    -0.06
     Performance
    -0.06
     Knee
    -0.06
    quisites
    -0.06
     thou
    -0.06
     ambassadors
    -0.06
    ента
    -0.06
    란
    -0.06
    gregation
    -0.06
    POSITIVE LOGITS
    goog
    0.07
    entionPolicy
    0.06
                                                ↵
    0.06
     조금
    0.06
     موج
    0.06
    crawl
    0.06
    _IT
    0.06
    /up
    0.06
    (post
    0.06
    たち
    0.06
    Act Density 0.056%

    No Known Activations