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

    Neuronpedia

    INDEX
    Explanations

    Non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    购物中心
    -0.07
    趴在
    -0.07
     sole
    -0.07
     mare
    -0.07
     תפ
    -0.07
     Lac
    -0.07
    .poi
    -0.07
    mal
    -0.07
    /articles
    -0.07
     md
    -0.07
    POSITIVE LOGITS
    剧情
    0.07
    ..↵↵
    0.07
    队友
    0.07
    –↵↵
    0.07
    埗
    0.07
    PRESENT
    0.06
    urbed
    0.06
    shint
    0.06
    ניס
    0.06
     dialect
    0.06
    Act Density 0.110%

    No Known Activations