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

    Neuronpedia

    INDEX
    Explanations

    youtube content and features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     video
    0.99
     Video
    0.93
     TikTok
    0.90
    视频
    0.90
    video
    0.88
    Video
    0.86
     وید
    0.86
     Streams
    0.85
     multimedia
    0.84
     videos
    0.83
    POSITIVE LOGITS
    俢
    0.77
    шали
    0.73
    policies
    0.70
     কমিটি
    0.69
     ermög
    0.67
    昇
    0.67
    修
    0.66
     ineligible
    0.66
    beri
    0.66
     bers
    0.65
    Act Density 0.026%

    No Known Activations