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

    Neuronpedia

    INDEX
    Explanations

    computing and wireless devices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    baby
    -0.08
    產
    -0.07
     british
    -0.07
     Tax
    -0.06
    忘了
    -0.06
     AMP
    -0.06
    第一次
    -0.06
    .assets
    -0.06
    FP
    -0.06
    either
    -0.06
    POSITIVE LOGITS
    这句话
    0.07
    廑
    0.07
     �
    0.06
    烜
    0.06
    泖
    0.06
    说到这里
    0.06
     {});↵
    0.06
     Goku
    0.06
    宠物
    0.06
    ();?>
    0.06
    Act Density 0.059%

    No Known Activations