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

    Neuronpedia

    INDEX
    Explanations

    Type classifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Type
    -0.90
     Stage
    -0.59
     Table
    -0.59
     Types
    -0.54
     typing
    -0.54
    zlib
    -0.51
     Be
    -0.49
     Internet
    -0.48
     Text
    -0.48
     Arr
    -0.48
    POSITIVE LOGITS
     AssemblyCulture
    1.06
    ⓧ
    0.92
    MemoryWarning
    0.89
    UnsafeEnabled
    0.81
     يتيمه
    0.78
    ">//
    0.76
    Obrázky
    0.73
     Roskov
    0.73
    StoryboardSegue
    0.72
     ProtoMessage
    0.71
    Act Density 1.540%

    No Known Activations