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

    Neuronpedia

    INDEX
    Explanations

    proper names with titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ตัว
    0.24
     اینکه
    0.23
     recomp
    0.23
    wifery
    0.23
    แกรม
    0.23
    此
    0.23
     Tumblr
    0.22
    brigen
    0.22
     ανθρώ
    0.22
    개
    0.22
    POSITIVE LOGITS
     Henrique
    0.29
     Singh
    0.28
     Rodriguez
    0.27
     Maria
    0.27
     Ahmad
    0.27
     Մ
    0.26
     Ivanov
    0.26
     midfielder
    0.25
     Иванович
    0.25
     劉
    0.25
    Act Density 0.015%

    No Known Activations