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

    Neuronpedia

    INDEX
    Explanations

    General English phrases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TagMode
    -0.86
    afficheront
    -0.78
    webElementXpaths
    -0.78
     <>",
    -0.75
    AndEndTag
    -0.73
    contentLoaded
    -0.73
     Roskov
    -0.72
    devamını
    -0.71
     بيها
    -0.69
     myſelf
    -0.68
    POSITIVE LOGITS
     fact
    0.76
     Facts
    0.69
     facts
    0.66
    Facts
    0.66
    Fact
    0.63
     Fact
    0.61
     FACTS
    0.55
    facts
    0.54
     FACT
    0.54
     hecho
    0.54
    Act Density 0.002%

    No Known Activations