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

    Neuronpedia

    INDEX
    Explanations

    css display properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ɫ
    0.40
    গ্ধ
    0.39
     échanc
    0.39
    ्हान
    0.39
    Provence
    0.38
     صغير
    0.37
    ڃ
    0.37
    শিরোনাম
    0.37
    Sliced
    0.37
    чью
    0.36
    POSITIVE LOGITS
     flex
    1.43
    flex
    1.37
     Flex
    1.27
    Flex
    1.22
     FLEX
    1.03
     flexing
    0.93
     fleks
    0.91
     flexDirection
    0.91
    grid
    0.88
     grid
    0.88
    Act Density 0.015%

    No Known Activations