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

    Neuronpedia

    INDEX
    Explanations

    will cover

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    સો
    0.76
    ાલુ
    0.72
    BarStyle
    0.71
    গুলে
    0.70
    iseite
    0.69
    chées
    0.66
    heiro
    0.66
    BibitemOpen
    0.64
    ர்ப
    0.64
     약간
    0.63
    POSITIVE LOGITS
     covers
    3.51
     covering
    3.47
     cover
    3.43
     coverage
    3.30
     Covers
    3.14
     Coverage
    3.13
     Covering
    3.10
    Coverage
    3.01
    covers
    2.98
    covering
    2.97
    Act Density 1.406%

    No Known Activations