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

    Neuronpedia

    INDEX
    Explanations

    areas and aspects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     berbagai
    0.87
    Quem
    0.85
    Datei
    0.74
    Gab
    0.68
    MOND
    0.66
    রকম
    0.66
     różnych
    0.66
    യില്ല
    0.64
     acompaña
    0.64
     முதலிய
    0.63
    POSITIVE LOGITS
     within
    0.91
     of
    0.90
     highlighted
    0.89
     where
    0.83
    ของการ
    0.79
     needing
    0.76
    ទៀត
    0.75
     covered
    0.75
     requiring
    0.75
     involved
    0.75
    Act Density 1.141%

    No Known Activations