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

    Neuronpedia

    INDEX
    Explanations

    lies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kenn
    -0.07
     inputFile
    -0.07
     parish
    -0.07
    Hex
    -0.06
     nano
    -0.06
    ขน
    -0.06
     annual
    -0.06
     rz
    -0.06
    -weight
    -0.06
    保密
    -0.06
    POSITIVE LOGITS
    ạo
    0.08
     QPoint
    0.07
    媆
    0.07
    一句
    0.07
     Chicago
    0.07
    ɩ
    0.07
    极大地
    0.07
    了
    0.06
    ocrates
    0.06
    علامات
    0.06
    Act Density 0.016%

    No Known Activations