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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    就跟
    -0.08
    윳
    -0.08
     cà
    -0.08
    >Error
    -0.07
    akış
    -0.07
    Ứ
    -0.07
    urrenc
    -0.07
    ᐟ
    -0.07
    ár
    -0.07
    POSITIVE LOGITS
     './
    0.08
     ^
    0.07
     ^↵
    0.07
     "<
    0.07
    '\
    0.07
    ()↵
    0.07
    共建
    0.07
      ↵
    0.06
    手游
    0.06
    青岛
    0.06
    Act Density 0.001%

    No Known Activations