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

    Neuronpedia

    INDEX
    Explanations

    words after decline, down, or illegal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     carer
    0.43
     banknotes
    0.42
     bourgeoisie
    0.40
     impotence
    0.38
     diarrhoea
    0.37
     difficulties
    0.37
     например
    0.36
     strikingly
    0.36
     debtors
    0.35
     morphism
    0.35
    POSITIVE LOGITS
     kiddos
    0.62
    はもちろん
    0.57
     हमारी
    0.54
    جميع
    0.54
     всех
    0.53
    當然
    0.53
     våra
    0.53
     tentunya
    0.52
     تمامی
    0.52
     всіх
    0.52
    Act Density 0.090%

    No Known Activations