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

    Neuronpedia

    INDEX
    Explanations

    book titles or subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nació
    0.42
     p
    0.41
     comenzó
    0.41
     L
    0.41
     Island
    0.40
     c
    0.40
     A
    0.40
     D
    0.40
     Railway
    0.40
     r
    0.40
    POSITIVE LOGITS
    喁
    0.43
    ární
    0.40
    ický
    0.40
    イメージ
    0.39
    Під
    0.38
    Если
    0.38
     लें
    0.37
    ьте
    0.37
    Maz
    0.37
    Компания
    0.35
    Act Density 0.005%

    No Known Activations