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

    Neuronpedia

    INDEX
    Explanations

    cover

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Έ
    -0.07
     School
    -0.07
     ו
    -0.07
    ู
    -0.07
     school
    -0.07
    ق
    -0.06
    북
    -0.06
    دي
    -0.06
    회의
    -0.06
     Revision
    -0.06
    POSITIVE LOGITS
     Idol
    0.07
    YNAM
    0.07
    .SaveChanges
    0.07
     ayında
    0.07
     Таким
    0.07
    (do
    0.07
     "\""
    0.07
     LinkedHashMap
    0.07
     drinking
    0.07
     Enjoy
    0.07
    Act Density 0.006%

    No Known Activations