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

    Neuronpedia

    INDEX
    Explanations

    inheritance, consensus, currency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     คะแนน
    0.43
     میلی
    0.39
     redirectTo
    0.38
     Skor
    0.38
    题材
    0.37
     മേഖ
    0.37
    姿勢
    0.37
    Rewrite
    0.36
     restre
    0.36
     rép
    0.36
    POSITIVE LOGITS
    accounts
    0.45
     करेंसी
    0.44
     accounts
    0.42
    tickets
    0.42
     Krone
    0.42
     permits
    0.41
    ads
    0.41
    idents
    0.40
     크라운
    0.40
    shims
    0.40
    Act Density 0.000%

    No Known Activations