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

    Neuronpedia

    INDEX
    Explanations

    html doctype declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ලු
    0.54
    によ
    0.51
    溝
    0.50
    $,
    0.49
    推奨
    0.49
    BSITE
    0.48
    を出
    0.47
    火力
    0.46
    Rpc
    0.46
     gute
    0.46
    POSITIVE LOGITS
     supremo
    0.66
     документ
    0.62
     <!
    0.62
    <html>
    0.60
     абсолю
    0.57
     सवार
    0.56
    DOCTYPE
    0.55
     dokumen
    0.55
    μεν
    0.55
    Dok
    0.54
    Act Density 0.012%

    No Known Activations