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

    Neuronpedia

    INDEX
    Explanations

    computer science/data analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dec
    -0.07
    产品
    -0.06
     CEOs
    -0.06
     Deck
    -0.06
    _hpp
    -0.06
    OURCE
    -0.06
     xp
    -0.06
     температура
    -0.06
    _from
    -0.06
    	initialize
    -0.06
    POSITIVE LOGITS
     collage
    0.06
    lever
    0.06
    �t
    0.06
    σταση
    0.06
    ver
    0.06
    lov
    0.06
    념
    0.06
     густ
    0.06
     contested
    0.06
    ��
    0.06
    Act Density 0.042%

    No Known Activations