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

    Neuronpedia

    INDEX
    Explanations

    function definition initiations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ianSpace
    0.38
     তথ
    0.34
    PERATURE
    0.34
     WILLIAMS
    0.34
    োনা
    0.34
    𝘇
    0.34
    ANNEL
    0.34
     Rooney
    0.34
     ಯಾವುದೇ
    0.34
    WATER
    0.33
    POSITIVE LOGITS
    init
    0.40
    8
    0.40
    1
    0.40
    make
    0.39
    4
    0.39
    5
    0.37
    up
    0.36
    initialize
    0.35
    6
    0.34
    Make
    0.34
    Act Density 0.178%

    No Known Activations