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

    Neuronpedia

    INDEX
    Explanations

    referring

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.56
     derselbe
    -0.49
    вік
    -0.46
     dieselben
    -0.46
    örös
    -0.45
     dieselbe
    -0.45
     AssemblyCompany
    -0.44
    occa
    -0.43
    час
    -0.43
     dafs
    -0.43
    POSITIVE LOGITS
    <bos>
    0.87
    Personendaten
    0.77
    bootstrapcdn
    0.75
     بيها
    0.66
    specifically
    0.65
    FormTagHelper
    0.63
     незавершена
    0.61
    Specifically
    0.61
     Specifically
    0.60
     specifically
    0.60
    Act Density 0.004%

    No Known Activations