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

    Neuronpedia

    INDEX
    Explanations

    C# namespaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unique
    0.81
     contenu
    0.80
     content
    0.78
    ᴥ
    0.77
     pacc
    0.75
    ⌣
    0.74
    unique
    0.73
    の内容
    0.73
     merci
    0.73
     исходя
    0.72
    POSITIVE LOGITS
    Collections
    1.45
     Collections
    1.23
    Drawing
    1.21
    Threading
    1.21
    Diagnostics
    1.21
    IO
    1.11
    Reflection
    1.11
    Globalization
    1.08
     collections
    1.06
    Buffers
    1.02
    Act Density 0.020%

    No Known Activations