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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that appear in award announcements, elections, and competition results including winner, champion, medal, official, and declared.

    oai_token-act-pair · gemini-2.0-flash

    winners

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     winners
    -1.16
     recipients
    -1.12
     Recipient
    -1.10
     Recipients
    -1.10
     recipient
    -1.09
    Winners
    -1.06
    winners
    -1.05
     winner
    -1.03
    Recipient
    -1.03
     Winners
    -1.02
    POSITIVE LOGITS
    +#+#
    0.78
    styleUrls
    0.67
    ArgumentParser
    0.64
    LookAnd
    0.63
    queryInterface
    0.59
    ंदीखरीदारी
    0.55
    adaptiveStyles
    0.54
    ymce
    0.53
     esternos
    0.52
    曖昧さ回避
    0.52
    Act Density 2.896%

    No Known Activations