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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Prom
    -0.07
    Important
    -0.07
     RS
    -0.06
    ключ
    -0.06
    逝
    -0.06
    orph
    -0.06
     Uns
    -0.06
     cél
    -0.06
    care
    -0.06
    scanner
    -0.06
    POSITIVE LOGITS
     [%
    0.07
    这个游戏
    0.07
     recognizer
    0.07
    姣
    0.07
    玩家们
    0.07
    आ
    0.07
     AREA
    0.07
     \"%
    0.07
     собственно
    0.07
     bụ
    0.07
    Act Density 0.125%

    No Known Activations