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

    Neuronpedia

    INDEX
    Explanations

    import streamlit as st

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pursuing
    1.14
     bask
    1.11
     conqu
    1.05
     diff
    1.05
     bast
    1.05
     preservatives
    1.04
     expect
    1.01
     tromb
    0.99
     sob
    0.98
     Gauss
    0.98
    POSITIVE LOGITS
    기
    1.08
    ان
    1.06
    ون
    1.06
     появился
    1.05
     विन
    1.05
     đúng
    1.04
    로
    1.03
     नामक
    1.00
    기와
    1.00
    ный
    0.99
    Act Density 0.000%

    No Known Activations