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

    Neuronpedia

    INDEX
    Explanations

    lists or bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ป็น
    0.77
     compds
    0.73
     specialises
    0.71
     является
    0.70
     agrícola
    0.67
    ში
    0.67
     Konink
    0.66
     utilises
    0.65
     Advertiser
    0.65
     canisters
    0.65
    POSITIVE LOGITS
     the
    1.07
    the
    0.98
     a
    0.92
     their
    0.80
    t
    0.77
     and
    0.74
    gt
    0.73
    s
    0.72
     an
    0.71
    l
    0.71
    Act Density 2.024%

    No Known Activations