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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AssemblyVersion
    -0.83
    +#+
    -0.83
     Vikipedi
    -0.77
    twimg
    -0.71
    Autoritní
    -0.71
    XmlAccessType
    -0.70
    DebuggerStep
    -0.70
     EconPapers
    -0.69
     وتسجيلات
    -0.69
    :✨
    -0.68
    POSITIVE LOGITS
     PRA
    0.43
     Jones
    0.43
    ligan
    0.43
     earthquake
    0.42
    流
    0.42
     earthquakes
    0.42
    сомо
    0.41
     Ouverture
    0.41
     campground
    0.41
    pos
    0.41
    Act Density 1.716%

    No Known Activations