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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thieves
    -0.07
    赫
    -0.07
    _FROM
    -0.07
     shaved
    -0.07
     Consult
    -0.06
     CAPITAL
    -0.06
     partes
    -0.06
     dataList
    -0.06
     Dil
    -0.06
     caps
    -0.06
    POSITIVE LOGITS
    ありがとう
    0.07
     unde
    0.07
     toch
    0.06
    A
    0.06
     transplant
    0.05
     &&↵
    0.05
    …it
    0.05
    ![↵
    0.05
     оди
    0.05
     جديد
    0.05
    Act Density 0.103%

    No Known Activations