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

    Neuronpedia

    INDEX
    Explanations

    pages, screens, views

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    8
    -1.50
    6
    -1.48
    5
    -1.39
    9
    -1.30
    7
    -1.20
    3
    -1.13
    </h2>
    -1.13
     ennen
    -1.12
    0
    -1.00
     เพื่อ
    -0.95
    POSITIVE LOGITS
    詐欺
    1.19
    ostruct
    1.11
     layout
    1.11
    Đây
    1.10
    お知らせ
    1.09
    cestor
    1.09
     implementar
    1.07
    飛行機
    1.04
    estima
    1.04
     кӀ
    1.02
    Act Density 0.077%

    No Known Activations