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

    Neuronpedia

    INDEX
    Explanations

    staff / employees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    亠
    1.12
    ্জ
    1.10
    l
    1.01
     demikian
    1.00
    ló
    0.98
    ل
    0.98
    碍
    0.98
     orientale
    0.97
    ायतों
    0.97
     Fame
    0.96
    POSITIVE LOGITS
    ງານ
    1.28
    员工
    1.13
    pesar
    1.08
     staffs
    1.05
    燹
    1.03
    ಖ
    1.02
     rosters
    1.02
     maest
    1.00
    ட்ட
    0.99
    dplyr
    0.98
    Act Density 0.089%

    No Known Activations