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

    Neuronpedia

    INDEX
    Explanations

    arxiv papers and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dani
    0.71
     Map
    0.68
    歌
    0.68
     DB
    0.67
     Db
    0.66
     song
    0.65
     consort
    0.64
    ೀಯ
    0.63
     mercy
    0.62
    Map
    0.61
    POSITIVE LOGITS
    eurs
    0.78
    ük
    0.75
    瞿
    0.75
    вей
    0.74
    ዚያ
    0.73
    тріш
    0.73
    relativistic
    0.73
    missione
    0.73
    បី
    0.73
    就知道
    0.71
    Act Density 0.009%

    No Known Activations