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

    Neuronpedia

    INDEX
    Explanations

    principle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Entrepreneurship
    -0.08
     entrepreneurship
    -0.08
    katapos
    -0.08
     Fal
    -0.07
     politikk
    -0.07
     Nol
    -0.07
     Entrepreneur
    -0.07
    ède
    -0.07
     Rein
    -0.07
     fal
    -0.07
    POSITIVE LOGITS
    /main
    0.12
    /master
    0.11
    ಮಂತ್ರಿ
    0.10
    మంత్రి
    0.10
    ‌ترین
    0.10
     utama
    0.10
    മന്ത്രി
    0.09
    /root
    0.09
    મંત્રી
    0.09
     principale
    0.09
    Act Density 0.074%

    No Known Activations