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

    Neuronpedia

    INDEX
    Explanations

    length or len

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    0.94
    iminary
    0.82
    اکي
    0.82
    utian
    0.81
    ➔
    0.80
    ContextCompat
    0.80
    otyping
    0.80
    ️⃣
    0.79
    ahal
    0.79
    дай
    0.79
    POSITIVE LOGITS
    и
    0.85
     vezes
    0.84
    ли
    0.83
     głów
    0.82
    ди
    0.77
     haies
    0.77
    пи
    0.76
    dür
    0.76
     кількість
    0.74
     cornea
    0.73
    Act Density 0.193%

    No Known Activations