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

    Neuronpedia

    INDEX
    Explanations

    online forums and posts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inkjet
    0.50
     printers
    0.48
     molds
    0.43
    SScript
    0.41
    📽
    0.41
     Printers
    0.40
     spotify
    0.40
     licensing
    0.40
    🚛
    0.40
     printing
    0.39
    POSITIVE LOGITS
    bbs
    0.84
     bbs
    0.77
     게시
    0.68
    帖子
    0.65
     BBS
    0.64
    贴
    0.59
    楼主
    0.59
    匿名
    0.59
    帖
    0.57
     forum
    0.55
    Act Density 0.003%

    No Known Activations