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

    Neuronpedia

    INDEX
    Explanations

    personal followed by abstract nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    人数
    0.44
    setParameter
    0.41
     pozitiv
    0.40
    ड्डी
    0.39
    Đ
    0.38
     Тере
    0.37
    くと
    0.37
    ハート
    0.37
    onn
    0.37
     功能
    0.37
    POSITIVE LOGITS
    izable
    0.70
    istic
    0.68
    ized
    0.67
    ised
    0.62
     preference
    0.59
    ization
    0.58
    izes
    0.58
    ização
    0.57
    izzazione
    0.55
    ities
    0.54
    Act Density 0.041%

    No Known Activations