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

    Neuronpedia

    INDEX
    Explanations

    uce

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     triệu
    -0.08
    539
    -0.07
    pre
    -0.07
    建設
    -0.07
    731
    -0.07
     chain
    -0.06
    812
    -0.06
    ·
    -0.06
     Therefore
    -0.06
    89
    -0.06
    POSITIVE LOGITS
    _Position
    0.07
     cs
    0.07
     시험
    0.06
    IMARY
    0.06
    texture
    0.06
     Bayer
    0.06
    .Bytes
    0.06
     ジ
    0.06
    iden
    0.06
     sagen
    0.06
    Act Density 0.040%

    No Known Activations