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

    Neuronpedia

    INDEX
    Explanations

    function set calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Վեր
    -0.91
     löytyy
    -0.90
    OnItem
    -0.86
     mußten
    -0.84
    lanze
    -0.84
    Another
    -0.83
    　＊
    -0.82
    Getting
    -0.82
     приходи
    -0.81
     consigue
    -0.81
    POSITIVE LOGITS
     set
    4.69
    set
    3.34
     sets
    2.59
     Set
    2.53
     setting
    2.44
    设置
    2.41
    Set
    2.30
     SET
    2.16
    セット
    2.14
     设置
    2.13
    Act Density 0.030%

    No Known Activations