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

    Neuronpedia

    INDEX
    Explanations

    family life and connections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lep
    0.39
    𝐋
    0.38
     pruned
    0.37
    ด
    0.36
    romagnet
    0.36
    mis
    0.35
     площа
    0.35
     রপ্ত
    0.35
    骋
    0.35
    儿子
    0.35
    POSITIVE LOGITS
     members
    0.75
    👪
    0.71
     member
    0.64
    成員
    0.61
    Family
    0.60
     Mitglieder
    0.57
    Members
    0.57
    成员
    0.56
     Family
    0.56
     membros
    0.55
    Act Density 0.014%

    No Known Activations