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

    Neuronpedia

    INDEX
    Explanations

    Halaman, Jó, Merhaba, Sultan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wär
    -0.76
    seco
    -0.74
    ঘ
    -0.74
    ন
    -0.73
    สิ
    -0.73
    জ
    -0.71
    码
    -0.71
    бели
    -0.71
    idist
    -0.70
     warum
    -0.69
    POSITIVE LOGITS
    Halaman
    0.88
    Jó
    0.74
    Merhaba
    0.74
     SPI
    0.73
    ニューアル
    0.73
    Sultan
    0.71
    をつける
    0.71
     Spitzen
    0.70
    AVERAGE
    0.69
    acaktır
    0.69
    Act Density 0.030%

    No Known Activations