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

    Neuronpedia

    INDEX
    Explanations

    section headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    သောအ
    0.46
    将在
    0.44
    美术
    0.42
     strangely
    0.42
     nine
    0.41
    λα
    0.40
     ćete
    0.40
     seven
    0.40
     नाइन
    0.39
     gồm
    0.39
    POSITIVE LOGITS
    訓練
    0.45
    介紹
    0.45
     train
    0.44
     numpy
    0.43
    numpy
    0.43
    streamlit
    0.43
    spruch
    0.43
     pandas
    0.42
     perpetrated
    0.42
     Numpy
    0.42
    Act Density 0.039%

    No Known Activations