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

    Neuronpedia

    INDEX
    Explanations

    unstable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stable
    -1.10
     stable
    -0.95
     Stable
    -0.90
     unstable
    -0.88
    Stable
    -0.85
    TagMode
    -0.78
     CreateTagHelper
    -0.77
    unstable
    -0.77
    __':
    -0.75
     NSCoder
    -0.75
    POSITIVE LOGITS
     StatefulWidget
    0.62
     bodies
    0.47
    AntiForgeryToken
    0.47
     vone
    0.45
     talk
    0.44
     subsoil
    0.44
     lease
    0.43
     rates
    0.42
    脚注の使い方
    0.42
     ranks
    0.41
    Act Density 0.312%

    No Known Activations