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

    Neuronpedia

    INDEX
    Explanations

    specific topics and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     séptimo
    0.44
    ául
    0.40
    四个
    0.40
     linguistique
    0.40
     やっ
    0.39
    ार्थियों
    0.39
    建筑物
    0.39
    ấ
    0.38
    football
    0.38
     ಅನೇಕ
    0.38
    POSITIVE LOGITS
     Mr
    0.49
     cependant
    0.44
     Chef
    0.43
     Secretary
    0.42
     CEO
    0.40
     promised
    0.40
     names
    0.40
     Naturally
    0.39
     Attorney
    0.39
     stall
    0.39
    Act Density 0.002%

    No Known Activations