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

    Neuronpedia

    INDEX
    Explanations

    videos and vlogs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intranet
    0.48
    Email
    0.43
    0.43
     conscientious
    0.42
    霭
    0.41
     trustworthiness
    0.39
     alumna
    0.39
     Considering
    0.38
     alveolar
    0.38
     odor
    0.38
    POSITIVE LOGITS
     영상을
    1.07
     videos
    1.05
     vídeo
    1.04
     vidéos
    1.03
     vídeos
    1.02
     ভিডিও
    1.02
     Vlog
    1.02
     відео
    1.00
     vlog
    1.00
     video
    0.98
    Act Density 0.257%

    No Known Activations