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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    离开了
    -0.08
     NPC
    -0.07
     wzglę
    -0.07
    (vm
    -0.07
    ū
    -0.07
    湉
    -0.06
     clans
    -0.06
     fled
    -0.06
    腺
    -0.06
     enraged
    -0.06
    POSITIVE LOGITS
    哏
    0.08
    买单
    0.08
    テスト
    0.08
     sửa
    0.07
    ը
    0.07
     Worksheet
    0.07
     wybór
    0.07
     GREEN
    0.07
     hát
    0.07
     Personally
    0.07
    Act Density 0.001%

    No Known Activations