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

    Neuronpedia

    INDEX
    Explanations

    American prisoners

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accelerated
    -0.07
    artin
    -0.07
    \Service
    -0.07
     Isn
    -0.07
     doen
    -0.07
    早餐
    -0.06
     التعاون
    -0.06
    كان
    -0.06
     �
    -0.06
    缈
    -0.06
    POSITIVE LOGITS
    .Enqueue
    0.07
    中国的
    0.07
    הק
    0.07
    END
    0.07
    ">↵
    0.07
    '))↵
    0.07
    ")
↵
    0.07
    )}
↵
    0.07
    王某
    0.07
    wanted
    0.07
    Act Density 0.028%

    No Known Activations