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

    Neuronpedia

    INDEX
    Explanations

    complementary words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    exion
    0.41
    arg
    0.38
    ပါ
    0.38
    ඍ
    0.37
    colors
    0.36
    野
    0.36
    alo
    0.36
    iston
    0.35
    alas
    0.35
     extant
    0.35
    POSITIVE LOGITS
     complements
    0.48
     nonsense
    0.46
     windmills
    0.46
     complement
    0.44
     dynamite
    0.44
     complementarity
    0.43
     complementary
    0.42
    趁
    0.41
     complémentaires
    0.41
     complementar
    0.40
    Act Density 0.004%

    No Known Activations