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

    Neuronpedia

    INDEX
    Explanations

    units, abbreviations, and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ய்ய
    0.76
    翩
    0.72
    妵
    0.69
    驰
    0.66
    冭
    0.65
    灿
    0.65
    壺
    0.65
    夭
    0.64
    বাদিক
    0.64
    ันทร์
    0.63
    POSITIVE LOGITS
     MG
    1.87
     TG
    1.87
     mg
    1.84
    pg
    1.84
     PG
    1.83
    mg
    1.81
     DG
    1.81
     LG
    1.81
    MG
    1.80
     lg
    1.79
    Act Density 1.230%

    No Known Activations