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

    Neuronpedia

    INDEX
    Explanations

    notice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    辈子
    -0.08
    _pipe
    -0.07
    一辈子
    -0.07
    _magic
    -0.07
    奋斗
    -0.07
    _portfolio
    -0.07
     indebted
    -0.07
    (E
    -0.07
     lavoro
    -0.07
     INC
    -0.07
    POSITIVE LOGITS
    登陆
    0.07
     lightly
    0.07
    Ⰽ
    0.07
    ﲬ
    0.07
     ↵    ↵
    0.06
    \Exception
    0.06
    伸
    0.06
    解放
    0.06
     العرا
    0.06
    输送
    0.06
    Act Density 0.002%

    No Known Activations