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

    Neuronpedia

    INDEX
    Explanations

    online shopping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    는
    0.81
    นี้
    0.79
    是
    0.76
    مس
    0.70
    مال
    0.69
    อน
    0.69
    مان
    0.68
    اط
    0.68
     be
    0.67
    0.66
    POSITIVE LOGITS
     Shopping
    0.90
     shopping
    0.82
    τε
    0.75
    i
    0.73
    n
    0.73
    ية
    0.72
     FEES
    0.72
    购物
    0.72
    shopping
    0.71
     Einkauf
    0.70
    Act Density 0.006%

    No Known Activations