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

    Neuronpedia

    INDEX
    Explanations

    START

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     khiển
    -0.07
    oz
    -0.07
     sociology
    -0.06
    plně
    -0.06
    FileName
    -0.06
     замен
    -0.06
    请输入
    -0.06
    PropertyName
    -0.06
     politician
    -0.06
    .testng
    -0.06
    POSITIVE LOGITS
    ooter
    0.07
    atisf
    0.06
    uated
    0.06
     ")
↵
    0.06
    uting
    0.06
     daughters
    0.06
    imest
    0.06
    particularly
    0.06
     Zust
    0.06
     ayak
    0.06
    Act Density 0.001%

    No Known Activations