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

    Neuronpedia

    INDEX
    Explanations

    scientific paper introductions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     denen
    -0.07
     neur
    -0.07
     detectors
    -0.06
     Adri
    -0.06
     IEnumerable
    -0.06
    548
    -0.06
    .contact
    -0.06
     Jehovah
    -0.06
     Jed
    -0.06
    Forge
    -0.06
    POSITIVE LOGITS
    _mentions
    0.07
     erfolgre
    0.06
    avail
    0.06
     Çin
    0.06
    ihu
    0.06
    Charlotte
    0.06
     Chairs
    0.06
     βά
    0.06
    طع
    0.06
     ubic
    0.06
    Act Density 0.014%

    No Known Activations