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

    Neuronpedia

    INDEX
    Explanations

    references to social media platforms and account metrics

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

    audience size

    np_acts-logits-general · gemini-2.0-flash

    millions of followers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalTable
    -0.71
    AddHtmlAttribute
    -0.64
    rungsseite
    -0.61
    出版年
    -0.55
    AddTagHelper
    -0.50
    WriteTagHelper
    -0.49
    MockBean
    -0.49
    IVEREF
    -0.46
    lateinit
    -0.46
    եմ
    -0.46
    POSITIVE LOGITS
     followers
    1.38
     millions
    1.19
    followers
    1.13
     Followers
    1.11
     follower
    1.09
    Followers
    1.06
     audience
    1.02
    millions
    1.01
     thousands
    1.00
     audiences
    0.98
    Act Density 0.079%

    No Known Activations