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

    Neuronpedia

    INDEX
    Explanations

    copy

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     நடிக்க
    0.77
    マネ
    0.73
     রাজার
    0.70
     Loaded
    0.70
     Jiménez
    0.69
     বাঙাল
    0.69
    searchText
    0.68
     Mariupol
    0.67
    Mountains
    0.67
     Quảng
    0.67
    POSITIVE LOGITS
    ilst
    0.63
     فه
    0.59
    ovie
    0.58
     cat
    0.58
    யில
    0.57
     endExpNow
    0.57
     interchangeable
    0.57
     فری
    0.56
    Cat
    0.56
    श्रे
    0.56
    Act Density 0.096%

    No Known Activations