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

    Neuronpedia

    INDEX
    Explanations

    correct

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ().↵
    -0.06
    ತ
    -0.06
    сл
    -0.06
    �认
    -0.06
    _stmt
    -0.06
    �
    -0.06
     nghĩa
    -0.06
    最高
    -0.06
    �
    -0.06
    Descri
    -0.06
    POSITIVE LOGITS
     resid
    0.07
     magazines
    0.07
     recibir
    0.07
    吗
    0.07
    ):\
    0.07
    鼐
    0.07
    沏
    0.07
    木耳
    0.07
     MF
    0.07
    FFE
    0.07
    Act Density 0.016%

    No Known Activations