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

    Neuronpedia

    INDEX
    Explanations

    mentions of advertising in apps

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

    advertisements

    np_acts-logits-general · gemini-2.0-flash

    advertising words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    曖昧さ回避
    -0.53
    BeginInit
    -0.52
     ddelweddau
    -0.51
    CloseOperation
    -0.49
    Scénario
    -0.49
    homonymie
    -0.48
    AndEndTag
    -0.48
     smtplib
    -0.47
    oa̍t
    -0.47
    _{+}
    -0.47
    POSITIVE LOGITS
     ad
    1.02
     ads
    1.01
     Ad
    0.94
     Ads
    0.88
     Display
    0.88
     advertisers
    0.88
     display
    0.87
    Ad
    0.86
     placements
    0.85
     advertiser
    0.83
    Act Density 0.154%

    No Known Activations