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

    Neuronpedia

    INDEX
    Explanations

    place and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    它
    2.13
    ug
    1.88
    ︎
    1.77
    DA
    1.75
    利亚
    1.71
    DR
    1.69
     spéciaux
    1.69
    BC
    1.63
    ST
    1.59
    MATIC
    1.57
    POSITIVE LOGITS
    zerű
    2.58
    ная
    2.31
     unwarranted
    2.25
    ями
    2.20
    しの
    2.19
    лені
    2.16
    ดังกล่าว
    2.11
    곳
    2.11
    ाम
    2.08
    يني
    2.08
    Act Density 0.109%

    No Known Activations