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

    Neuronpedia

    INDEX
    Explanations

    Question:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ஏற்ற
    0.88
    ের
    0.79
     serm
    0.75
    $\
    0.74
     \\
    0.71
    $(\
    0.71
    elez
    0.70
    styl
    0.70
    thed
    0.69
    িশালী
    0.68
    POSITIVE LOGITS
     پوچھ
    0.87
     고민
    0.83
    ूंगा
    0.81
     morphisms
    0.78
     penjumlahan
    0.77
     myśl
    0.77
     जरा
    0.76
     lanjut
    0.74
     desafío
    0.74
     pytanie
    0.74
    Act Density 0.027%

    No Known Activations