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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations/acronyms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >Contact
    -0.27
    urai
    -0.27
    CTYPE
    -0.26
    RTL
    -0.26
     ìĿĺ
    -0.26
    åıij
    -0.25
    Simulation
    -0.25
     simulation
    -0.25
     métier
    -0.24
     getOrder
    -0.24
    POSITIVE LOGITS
    è¡¡
    0.33
     taught
    0.29
    _learn
    0.28
    learn
    0.27
     tut
    0.26
    ãĤĨ
    0.26
    Loan
    0.25
    鼷éĶĭ
    0.25
    iences
    0.24
    æĸ°ä¸ī
    0.24
    Act Density 0.001%

    No Known Activations