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

    Neuronpedia

    INDEX
    Explanations

    designed to be adaptable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     obedience
    0.45
     a
    0.42
     adhesion
    0.41
    scalars
    0.41
    obedience
    0.41
     cards
    0.40
     similarly
    0.39
     lucrative
    0.39
    cards
    0.39
     adherence
    0.39
    POSITIVE LOGITS
    ieux
    0.50
    ungsl
    0.49
     amikor
    0.43
    EventManager
    0.42
     मॉ
    0.42
     Chirurgien
    0.41
     Consultez
    0.41
     পেতে
    0.41
     Bestell
    0.41
    နိုင်ငံ
    0.40
    Act Density 0.002%

    No Known Activations