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

    Neuronpedia

    INDEX
    Explanations

    before " or "articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Javadoc
    0.40
     Herren
    0.40
    Parsing
    0.39
    宽
    0.39
     κον
    0.39
     обита
    0.38
    长度
    0.38
    Annex
    0.38
    ጥረ
    0.37
     molecules
    0.37
    POSITIVE LOGITS
     แท
    0.48
     feta
    0.47
    aio
    0.47
     VoIP
    0.47
     ajj
    0.46
    ភ្ជាប់
    0.46
    fried
    0.46
     modernize
    0.45
     RAR
    0.45
     kaisi
    0.44
    Act Density 0.002%

    No Known Activations