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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values and rounding concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Round" followed by a letter

    np_acts-logits-general · gemini-2.0-flash

    rounding numerical values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    migrationBuilder
    -0.87
    cookieParser
    -0.76
    XmlAccessorType
    -0.76
    rrggbb
    -0.72
    PMailer
    -0.66
    спубли
    -0.64
    PreferredItem
    -0.64
     AssemblyCompany
    -0.62
    webElementGuid
    -0.61
    CloseOperation
    -0.61
    POSITIVE LOGITS
    trip
    0.94
     robin
    0.87
     rounds
    0.84
    round
    0.83
    robin
    0.80
     ROUND
    0.80
     round
    0.79
    rounds
    0.76
     trip
    0.76
    Round
    0.74
    Act Density 0.052%

    No Known Activations