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

    Neuronpedia

    INDEX
    Explanations

    social network posts and updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transducers
    0.52
     intakes
    0.47
     dilutions
    0.46
     gripper
    0.45
     parenchyma
    0.44
     inhomogeneities
    0.44
     adaptability
    0.43
    uarine
    0.43
     glazing
    0.43
     distinguishers
    0.43
    POSITIVE LOGITS
    好友
    1.11
     posting
    1.02
     Posting
    0.99
    Posts
    0.98
     posts
    0.97
     Posts
    0.95
     friends
    0.94
     친구
    0.91
     Friends
    0.90
    帖子
    0.90
    Act Density 0.042%

    No Known Activations