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

    Neuronpedia

    INDEX
    Explanations

    links in markdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     WG
    0.37
    ualan
    0.36
    γον
    0.35
     WM
    0.35
     Kimberly
    0.34
     Drilling
    0.34
     Edvard
    0.34
    творю
    0.34
    Judy
    0.34
     Digests
    0.33
    POSITIVE LOGITS
    <<"
    0.38
    ಚ
    0.38
     dove
    0.37
    잿
    0.36
    پاک
    0.35
     коричне
    0.35
    ষ্টার
    0.35
     কট
    0.35
     khawatir
    0.35
    宸
    0.34
    Act Density 0.001%

    No Known Activations