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

    Neuronpedia

    INDEX
    Explanations

    safety

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     κυ
    -0.07
    ospels
    -0.07
    .items
    -0.07
    urls
    -0.07
     QMap
    -0.06
     Hosting
    -0.06
     Вели
    -0.06
    _linear
    -0.06
     Booking
    -0.06
    wargs
    -0.06
    POSITIVE LOGITS
     millenn
    0.07
    nid
    0.07
    ivě
    0.06
     sortBy
    0.06
    找
    0.06
     &(
    0.06
     aracı
    0.06
     ไม
    0.06
     neby
    0.06
    ’nde
    0.06
    Act Density 0.025%

    No Known Activations