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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MA
    -0.07
     []);↵
    -0.07
     Elsa
    -0.07
    Large
    -0.06
    $array
    -0.06
    .shopping
    -0.06
    EXIST
    -0.06
     ';
    -0.06
     própria
    -0.06
     chụp
    -0.06
    POSITIVE LOGITS
     backing
    0.07
    岗位
    0.07
    .Ad
    0.07
     pope
    0.07
     accommodations
    0.07
    Age
    0.07
    スポ
    0.07
    Dog
    0.07
    Layer
    0.07
     Xml
    0.07
    Act Density 0.054%

    No Known Activations