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

    Neuronpedia

    INDEX
    Explanations

    ARN

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tập
    -0.08
    慢慢
    -0.07
    (@"%@",
    -0.07
     wool
    -0.07
    _hook
    -0.07
     Walt
    -0.06
     chac
    -0.06
     zostały
    -0.06
    Mui
    -0.06
     cunt
    -0.06
    POSITIVE LOGITS
    鏖
    0.08
    𝘮
    0.08
    阙
    0.08
    奔驰
    0.07
    Connected
    0.07
    富贵
    0.07
    ղ
    0.07
    פקיד
    0.07
     Existing
    0.07
    겙
    0.07
    Act Density 0.001%

    No Known Activations