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

    Neuronpedia

    INDEX
    Explanations

    plagiarism and academic integrity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.69
    invest
    0.66
    mental
    0.66
    low
    0.65
    لی
    0.65
    leri
    0.63
    graph
    0.61
    ine
    0.60
    ali
    0.58
    া
    0.58
    POSITIVE LOGITS
     plagiarism
    0.90
     plag
    0.73
    巽
    0.70
    agiarism
    0.66
     வால்பேப்பர்கள்
    0.64
    ן
    0.64
     atthakath
    0.64
    lyPlugin
    0.64
    న్స్
    0.62
    ۇ
    0.62
    Act Density 0.032%

    No Known Activations