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

    Neuronpedia

    INDEX
    Explanations

    _start

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deleted
    -0.07
    Bulletin
    -0.07
     breakfast
    -0.06
     lieutenant
    -0.06
     xrange
    -0.06
    Б
    -0.06
    Li
    -0.06
     Uncomment
    -0.06
    عداد
    -0.06
     simultaneous
    -0.06
    POSITIVE LOGITS
     chăm
    0.08
    (Card
    0.07
    政策
    0.06
     وقد
    0.06
    .`|`↵
    0.06
    enville
    0.06
    SubMenu
    0.06
    Interface
    0.06
    .Util
    0.06
    .emit
    0.06
    Act Density 0.001%

    No Known Activations