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

    Neuronpedia

    INDEX
    Explanations

    ultimately. fracturing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лэ
    0.84
     sofern
    0.80
     solic
    0.77
    স্বাধীনতা
    0.77
    высо
    0.76
    し
    0.75
     vocês
    0.74
    স
    0.74
     bracelet
    0.73
     möglicherweise
    0.72
    POSITIVE LOGITS
    潘
    0.73
     économiques
    0.71
     العلوم
    0.66
     VALLEY
    0.66
    廡
    0.65
     Dünya
    0.64
     뜻
    0.63
    aved
    0.63
     Mercantile
    0.62
     ไทย
    0.61
    Act Density 0.001%

    No Known Activations