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

    Neuronpedia

    INDEX
    Explanations

    catch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     phải
    -0.07
     Throne
    -0.07
     cứ
    -0.06
    	mkdir
    -0.06
    ut
    -0.06
    NFL
    -0.06
    produto
    -0.06
    _kategori
    -0.06
     festive
    -0.06
    gota
    -0.06
    POSITIVE LOGITS
     substituted
    0.07
     transporting
    0.06
    이드
    0.06
    tep
    0.06
    isay
    0.06
    تماع
    0.06
    орт
    0.06
     importing
    0.06
     superiority
    0.06
     substitute
    0.06
    Act Density 0.008%

    No Known Activations