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

    Neuronpedia

    INDEX
    Explanations

    social media hashtags

    np_acts-logits-general · gemini-2.5-flash-lite

    mentions of social media influencers/accounts and their platform/profile details (platform names, follower counts, content and links).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Negative Logits
    ا
    0.70
    α
    0.67
    屐
    0.67
    arquivo
    0.57
     XHTML
    0.56
    Nuclear
    0.55
    Ath
    0.55
     Nuclear
    0.54
     inglese
    0.54
    Insurance
    0.53
    POSITIVE LOGITS
     Instagram
    1.00
     TikTok
    0.92
     hashtags
    0.91
     selfies
    0.90
     instagram
    0.88
     selfie
    0.88
    Instagram
    0.88
     tiktok
    0.87
     Twitter
    0.86
     Snapchat
    0.86
    Act Density 0.473%

    No Known Activations