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

    Neuronpedia

    INDEX
    Explanations

    code initialization methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.53
    |
    0.47
     have
    0.42
     아이
    0.42
     [
    0.41
     org
    0.41
    │
    0.40
     href
    0.40
     (
    0.39
     limit
    0.39
    POSITIVE LOGITS
    Przeczytaj
    0.45
    िस्तान
    0.44
    <unused71>
    0.42
    elevationMap
    0.42
    ઞ
    0.40
    <unused17>
    0.40
    肽
    0.40
    pieceSelection
    0.39
    <unused21>
    0.38
    aucune
    0.38
    Act Density 0.214%

    No Known Activations