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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.52
    offsetof
    -0.51
     været
    -0.50
     (£
    -0.49
    illian
    -0.49
     còn
    -0.49
     NSCoder
    -0.48
    WriteBarrier
    -0.48
     وتسجيلات
    -0.48
    <tfoot>
    -0.47
    POSITIVE LOGITS
    IUrlHelper
    0.68
     виправивши
    0.65
     "
    0.62
     “
    0.60
    「
    0.58
     sayin
    0.53
    usermodel
    0.52
    “
    0.52
    geable
    0.52
     Signalez
    0.52
    Act Density 0.006%

    No Known Activations