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

    Neuronpedia

    INDEX
    Explanations

    function as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ag
    2.14
    у
    2.02
    il
    1.93
    ї
    1.88
    ט
    1.87
    ят
    1.86
    ل
    1.83
    म
    1.80
    ну
    1.74
    يد
    1.73
    POSITIVE LOGITS
    metaTag
    2.02
     ecstasy
    1.94
     aast
    1.91
     surgi
    1.89
    ンの
    1.88
     keresztül
    1.88
     admirably
    1.87
    mmm
    1.84
     myFunction
    1.84
    Еще
    1.83
    Act Density 0.497%

    No Known Activations