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

    Neuronpedia

    INDEX
    Explanations

    root

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interchange
    -0.07
     irr
    -0.07
     advertisement
    -0.07
     pare
    -0.07
     asynchronously
    -0.07
     sey
    -0.06
     Symphony
    -0.06
     monstr
    -0.06
     कह
    -0.06
     خی
    -0.06
    POSITIVE LOGITS
     Root
    0.11
    Root
    0.10
     root
    0.09
     Roots
    0.08
    랍니다
    0.08
     roots
    0.08
    roots
    0.08
    root
    0.08
    /root
    0.07
    (root
    0.07
    Act Density 0.016%

    No Known Activations