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

    Neuronpedia

    INDEX
    Explanations

    latex markup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     toget
    0.55
     αλλά
    0.52
    بة
    0.50
     Técn
    0.49
     Será
    0.48
     Dön
    0.47
     DeConcini
    0.46
    ை
    0.46
    ኋ
    0.46
     등의
    0.45
    POSITIVE LOGITS
    usepackage
    0.48
    dl
    0.41
    description
    0.40
    tables
    0.39
    eli
    0.39
    tbl
    0.39
    双
    0.39
    titulo
    0.39
    秒
    0.39
    tic
    0.38
    Act Density 0.006%

    No Known Activations