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

    Neuronpedia

    INDEX
    Explanations

    the [word starting with d, c, l]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ны
    0.88
    ות
    0.88
     машиналары
    0.84
    rocessing
    0.82
    ాల
    0.82
     машиналарын
    0.82
    मा
    0.81
    ك
    0.81
    িয়াল
    0.80
    нные
    0.79
    POSITIVE LOGITS
    พ์
    0.84
    东西
    0.81
     crédit
    0.81
     fédéral
    0.79
     ৃ
    0.78
     öğrend
    0.77
    tı
    0.77
     véritable
    0.77
    样子
    0.76
    zelfde
    0.76
    Act Density 0.250%

    No Known Activations