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

    Neuronpedia

    INDEX
    Explanations

    programming imports

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ჷ
    0.62
    ͆
    0.59
    )^{[\
    0.58
     सहानु
    0.57
     dharm
    0.57
     خۆ
    0.56
     思う
    0.56
    xyplot
    0.55
    बंधनाच्या
    0.55
    螫
    0.55
    POSITIVE LOGITS
    import
    0.86
     import
    0.81
    ,
    0.61
    from
    0.59
     from
    0.56
    os
    0.52
    arg
    0.52
    ↵
    0.51
     as
    0.50
     నుండి
    0.46
    Act Density 0.092%

    No Known Activations