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

    Neuronpedia

    INDEX
    Explanations

    array

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    World
    -0.07
    .should
    -0.07
    ��态
    -0.07
     should
    -0.06
     رب
    -0.06
    コミュニケーション
    -0.06
     لهذا
    -0.06
    "group
    -0.06
    sounds
    -0.06
    scope
    -0.06
    POSITIVE LOGITS
    .Empty
    0.07
    湖北
    0.07
    Contained
    0.07
     uncle
    0.07
     UNICODE
    0.07
    체
    0.07
    olini
    0.07
    广西
    0.07
     uns
    0.07
     اللقاء
    0.07
    Act Density 0.006%

    No Known Activations