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

    Neuronpedia

    INDEX
    Explanations

    practical strategy, live encyclopedia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    بی
    0.42
     desperately
    0.40
    陨
    0.40
     rose
    0.40
    荧
    0.39
     vert
    0.39
     stood
    0.38
     artes
    0.38
    芸術
    0.38
     cerim
    0.38
    POSITIVE LOGITS
    colon
    0.41
    "))
    0.39
     পত্রিকাটি
    0.36
    фіка
    0.35
    macosx
    0.34
    ")))
    0.34
     ಹೆಚ್ಚ
    0.34
    workbook
    0.34
     نخ
    0.34
    RQ
    0.34
    Act Density 0.001%

    No Known Activations