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

    Neuronpedia

    INDEX
    Explanations

    Prejudice and bias

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    �
    -0.08
    រ
    -0.08
     dus
    -0.08
    ｩ
    -0.07
    _INSTALL
    -0.07
     ذو
    -0.07
    _UART
    -0.07
     Tanzania
    -0.07
    뭇
    -0.07
    POSITIVE LOGITS
     đệ
    0.07
    请及时
    0.07
    被告
    0.07
    据
    0.07
    Death
    0.06
     Forever
    0.06
     Publication
    0.06
    secutive
    0.06
     pope
    0.06
     unfavor
    0.06
    Act Density 0.037%

    No Known Activations