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

    Neuronpedia

    INDEX
    Explanations

    find out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     పరిస్థ
    0.48
     لوبې
    0.44
    骠
    0.43
     situatie
    0.42
    ⦖
    0.42
    푞
    0.42
     ponencia
    0.41
    FreeFlag
    0.41
    тится
    0.41
    コマンド
    0.40
    POSITIVE LOGITS
     this
    0.54
    are
    0.50
     to
    0.50
    ↵
    0.48
    this
    0.48
     Tok
    0.47
     NASA
    0.47
     that
    0.46
     in
    0.46
     Brazil
    0.46
    Act Density 0.006%

    No Known Activations