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

    Neuronpedia

    INDEX
    Explanations

    first-person singular pronoun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝐢
    -1.90
    你就
    -1.75
     ندار
    -1.70
    你是不是
    -1.52
    那你
    -1.50
     xxiv
    -1.46
     esquer
    -1.45
     territo
    -1.45
    べし
    -1.44
    你说
    -1.43
    POSITIVE LOGITS
     I
    8.63
     אני
    3.81
     my
    3.77
     tôi
    3.70
    ผม
    3.23
     я
    3.20
     me
    2.92
     мне
    2.77
    私は
    2.75
     jsem
    2.66
    Act Density 2.289%

    No Known Activations