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

    Neuronpedia

    INDEX
    Explanations

    links and resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pasture
    0.74
     gosh
    0.74
     happens
    0.73
     pastures
    0.69
    useState
    0.66
    Влади
    0.66
    টাল
    0.63
     und
    0.62
     takim
    0.62
     mitochondria
    0.61
    POSITIVE LOGITS
    োরে
    0.68
    ोटोरोला
    0.68
     ક્ષ
    0.67
    میٹ
    0.65
    ាទ
    0.64
    Ớ
    0.64
    opard
    0.64
    ங்கே
    0.63
    ূর্ন
    0.62
    byshev
    0.62
    Act Density 0.214%

    No Known Activations