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

    Neuronpedia

    INDEX
    Explanations

    Recurrent neural networks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    upas
    0.75
    uple
    0.73
    getHeader
    0.71
     ku
    0.68
     헤
    0.67
    ั่ว
    0.67
    uke
    0.66
     parallèles
    0.65
    ukone
    0.65
     स्कूटर
    0.64
    POSITIVE LOGITS
    院
    0.69
    لاص
    0.62
    キャリア
    0.60
    ্দ
    0.60
     Бо
    0.59
     Co
    0.58
    NAL
    0.58
     бо
    0.57
    การณ์
    0.57
     सुरेंद्र
    0.57
    Act Density 0.008%

    No Known Activations