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

    Neuronpedia

    INDEX
    Explanations

    buying or selling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nf
    0.52
    кри
    0.51
    وريا
    0.51
    ostiene
    0.51
     invoke
    0.50
     hanno
    0.50
     funcionan
    0.47
    тину
    0.47
     db
    0.46
    ciendo
    0.46
    POSITIVE LOGITS
    bt
    0.46
     محصول
    0.45
    快速
    0.45
     شراء
    0.44
    prices
    0.44
     Ke
    0.43
     Hike
    0.42
     محصولات
    0.42
    Credentials
    0.41
    开拓
    0.41
    Act Density 0.000%

    No Known Activations