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

    Neuronpedia

    INDEX
    Explanations

    breakdown how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     χρη
    0.43
     السؤال
    0.43
     spør
    0.41
    ির্ব
    0.39
    optimizers
    0.39
    ICIENCY
    0.39
     повы
    0.39
    㧋
    0.39
     naprawdę
    0.38
     otáz
    0.38
    POSITIVE LOGITS
     methodology
    0.82
     approach
    0.75
    如何
    0.75
     designing
    0.75
    解决方案
    0.71
     how
    0.70
    どのように
    0.68
     planning
    0.68
    howto
    0.67
     계획
    0.66
    Act Density 0.003%

    No Known Activations