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

    Neuronpedia

    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _index
    -0.07
    ा↵↵
    -0.07
     categories
    -0.06
    outline
    -0.06
     EL
    -0.06
     kle
    -0.06
     Enables
    -0.06
    IVITY
    -0.06
    '↵
    -0.06
    개를
    -0.06
    POSITIVE LOGITS
     deco
    0.06
    라피
    0.06
    パン
    0.06
     캐
    0.06
    (duration
    0.06
    上传
    0.06
    :a
    0.06
    .HttpServlet
    0.05
    보기
    0.05
     plight
    0.05
    Act Density 0.179%

    No Known Activations