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

    Neuronpedia

    INDEX
    Explanations

    child widget or children

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ką
    0.91
    ’
    0.86
    -
    0.84
     ajoute
    0.80
    Cxx
    0.79
     complète
    0.78
    RENCY
    0.77
     étudi
    0.76
    cL
    0.76
    ElementName
    0.76
    POSITIVE LOGITS
    는
    1.16
     in
    1.09
    是
    0.96
    は
    0.90
    ۔
    0.89
     with
    0.89
    కు
    0.86
     and
    0.84
    s
    0.83
     not
    0.82
    Act Density 0.006%

    No Known Activations