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

    Neuronpedia

    INDEX
    Explanations

    country or location names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exporters
    -0.85
     exporter
    -0.83
    ophone
    -0.75
    spre
    -0.73
    inos
    -0.71
    exporter
    -0.66
     tfsi
    -0.61
     novels
    -0.60
    ghan
    -0.59
    ophones
    -0.58
    POSITIVE LOGITS
    UnsafeEnabled
    0.68
    StoryboardSegue
    0.59
     religieuses
    0.57
    yscale
    0.52
     devoirs
    0.51
     leçons
    0.49
    DoubleQuotes
    0.48
     @"/
    0.47
    ed
    0.47
    tagHelper
    0.46
    Act Density 0.393%

    No Known Activations