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

    Neuronpedia

    INDEX
    Explanations

    research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    中期
    -0.08
    🅼
    -0.08
    村
    -0.07
    黼
    -0.07
     national
    -0.06
    媂
    -0.06
    _aspect
    -0.06
     Daw
    -0.06
    场均
    -0.06
     box
    -0.06
    POSITIVE LOGITS
    瞳
    0.07
     ללכת
    0.07
     Ш
    0.07
    🧭
    0.07
     servant
    0.07
     playa
    0.07
     Ferry
    0.06
     <!--
    0.06
    ())↵↵↵
    0.06
     Config
    0.06
    Act Density 0.087%

    No Known Activations