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

    Neuronpedia

    INDEX
    Explanations

    Key improvements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    血糖
    0.40
     Rex
    0.39
    綱
    0.39
    괘
    0.38
     managable
    0.38
    Rece
    0.37
     गेंद
    0.37
     neque
    0.37
    নাই
    0.36
    eb
    0.36
    POSITIVE LOGITS
    Angel
    0.39
     Hindus
    0.38
     Angel
    0.38
     Mush
    0.37
    Maya
    0.37
     Hindu
    0.37
     இந்து
    0.36
     Dharm
    0.36
     Hinduism
    0.36
     Phas
    0.36
    Act Density 0.010%

    No Known Activations