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

    Neuronpedia

    INDEX
    Explanations

    twitter and tweets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Youtube
    0.68
     YouTube
    0.64
     Facebook
    0.63
     Tiktok
    0.58
     youtube
    0.55
     काम
    0.55
     TikTok
    0.55
     फेसबुक
    0.54
     यूट्यूब
    0.52
    Youtube
    0.51
    POSITIVE LOGITS
    Twitter
    0.68
    O
    0.61
    ých
    0.57
    ómetro
    0.57
    ad
    0.56
     Twitter
    0.55
    v
    0.54
    J
    0.54
    Tweet
    0.53
    N
    0.53
    Act Density 0.008%

    No Known Activations