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

    Neuronpedia

    INDEX
    Explanations

    specifying types or categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uiu
    0.35
    ქ
    0.34
    getRedTeam
    0.34
    okeh
    0.33
    这一切
    0.33
     Vass
    0.33
    жом
    0.31
    ޤ
    0.31
    ᱑
    0.31
    പടി
    0.31
    POSITIVE LOGITS
     types
    3.88
     type
    3.70
    类型
    3.39
     tipo
    3.38
     jenis
    3.31
    types
    3.30
     tipos
    3.27
     نوع
    3.20
    type
    3.13
     loại
    3.08
    Act Density 0.562%

    No Known Activations