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

    Neuronpedia

    INDEX
    Explanations

    purposes only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ที่เรา
    1.57
     ไอ้
    1.20
     MANY
    1.20
     Beaucoup
    1.18
     woes
    1.17
     misfortunes
    1.17
    很多
    1.13
     неправи
    1.11
     우리가
    1.11
    很多的
    1.11
    POSITIVE LOGITS
    etable
    1.11
    edel
    1.08
    uang
    1.06
    mnt
    1.01
    rangle
    1.01
    escal
    0.98
    anation
    0.97
     rollup
    0.97
     manip
    0.97
     summon
    0.96
    Act Density 0.115%

    No Known Activations