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

    Neuronpedia

    INDEX
    Explanations

    consideration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    尚未
    -0.07
     الاخ
    -0.07
     acronym
    -0.07
    ạo
    -0.07
    红酒
    -0.06
     Edmonton
    -0.06
    逆行
    -0.06
    摈
    -0.06
    Todd
    -0.06
    Tony
    -0.06
    POSITIVE LOGITS
    -Agent
    0.07
    _RESULTS
    0.07
     mocker
    0.07
     serializer
    0.07
    _LEVEL
    0.07
    轳
    0.07
    _features
    0.07
    ߍ
    0.06
    (element
    0.06
    0.06
    Act Density 0.010%

    No Known Activations