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

    Neuronpedia

    INDEX
    Explanations

    porcelain dolls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    1.66
    es
    1.58
    ing
    1.49
    बाई
    1.44
    enos
    1.41
    ة
    1.41
    ist
    1.39
    iniai
    1.36
    iti
    1.35
    ed
    1.33
    POSITIVE LOGITS
    TOM
    1.70
    TEM
    1.56
     porcel
    1.55
    TW
    1.53
    TEX
    1.52
     snugly
    1.52
    suz
    1.51
    TZ
    1.49
    ル
    1.48
    PA
    1.46
    Act Density 0.002%

    No Known Activations