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

    Neuronpedia

    INDEX
    Explanations

    article beginnings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    。その
    -0.07
     Alma
    -0.07
    _ent
    -0.07
    rending
    -0.06
     datastore
    -0.06
     cảm
    -0.06
    .display
    -0.06
     Ein
    -0.06
     参
    -0.06
     parçası
    -0.06
    POSITIVE LOGITS
    ไปย
    0.06
    �
    0.06
     misma
    0.06
    密
    0.06
     Лит
    0.06
    Sync
    0.06
    ()',
    0.06
    -bre
    0.06
    crawl
    0.06
    idx
    0.06
    Act Density 0.096%

    No Known Activations