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

    Neuronpedia

    INDEX
    Explanations

    my creators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    నే
    0.30
    ăț
    0.29
    াভাবিক
    0.28
     marquee
    0.27
     board
    0.26
     receiving
    0.26
     deferred
    0.26
    atched
    0.26
     prisms
    0.26
    σό
    0.26
    POSITIVE LOGITS
    特別
    0.35
     nums
    0.35
    oxide
    0.34
    ptr
    0.34
    ciju
    0.32
     特別
    0.31
     rectum
    0.31
     ऑक्साइड
    0.31
     ansch
    0.31
     /(\
    0.30
    Act Density 0.004%

    No Known Activations