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

    Neuronpedia

    INDEX
    Explanations

    elements related to email communication and spam filtering

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

    captcha, SPAM, images, mail

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stdc
    -0.51
    Filmografie
    -0.47
     UILabel
    -0.41
     Kings
    -0.40
    riwal
    -0.39
    HelloWorld
    -0.39
    abancı
    -0.38
    SneakyThrows
    -0.38
    KommentareTeilen
    -0.38
     Harrington
    -0.38
    POSITIVE LOGITS
    ismet
    0.60
    MessageTagHelper
    0.50
    webElementXpaths
    0.50
    photobucket
    0.48
    Personendaten
    0.46
    Darn
    0.45
    haikusbot
    0.43
    IsMutable
    0.43
    ագրություններ
    0.43
     Disqus
    0.42
    Act Density 0.347%

    No Known Activations