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

    Neuronpedia

    INDEX
    Explanations

    remove buildup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     QR
    0.50
     vermek
    0.49
     nanti
    0.47
     saad
    0.46
     costing
    0.45
    end
    0.45
     seiner
    0.44
     diperoleh
    0.44
     verkrij
    0.44
     bruker
    0.43
    POSITIVE LOGITS
    Shin
    0.51
    Tổng
    0.51
    Вакан
    0.49
    Dijstra
    0.49
    Tham
    0.48
    Cir
    0.48
    Expect
    0.47
    Variety
    0.47
    Flame
    0.47
     উভ
    0.46
    Act Density 0.004%

    No Known Activations