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

    Neuronpedia

    INDEX
    Explanations

    fall, especially, roll

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    esque
    0.53
    ב
    0.53
     used
    0.48
    وای
    0.47
    ed
    0.47
    מית
    0.46
     could
    0.46
    データ
    0.46
    This
    0.46
    к
    0.46
    POSITIVE LOGITS
     ElevatedButton
    0.50
     녹
    0.48
     trồng
    0.46
     नोंद
    0.46
     المت
    0.45
    🧼
    0.45
    PathDirectory
    0.45
     عش
    0.44
    attup
    0.44
     күн
    0.44
    Act Density 0.001%

    No Known Activations