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

    Neuronpedia

    INDEX
    Explanations

    facts about entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zoveel
    0.43
    我们需要
    0.42
     संभावित
    0.42
     nostre
    0.41
     ง่าย
    0.41
    ကယ်
    0.41
     സു
    0.40
     prochain
    0.40
     mūsų
    0.40
     нужно
    0.39
    POSITIVE LOGITS
     Wikipedia
    0.57
    Wikipedia
    0.48
    ,[
    0.46
     Wikimedia
    0.45
     wikipedia
    0.44
     /ˈ
    0.44
     Encyclopædia
    0.42
     chiefly
    0.42
    Wikimedia
    0.41
     histori
    0.40
    Act Density 0.204%

    No Known Activations