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

    Neuronpedia

    INDEX
    Explanations

    data collection and storage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     निभाने
    0.39
    埆
    0.39
    াশ
    0.38
     세율
    0.38
    ूठी
    0.37
    橛
    0.37
     شوق
    0.36
     Flügel
    0.36
     Nucleaires
    0.35
    箬
    0.35
    POSITIVE LOGITS
     data
    2.70
    data
    2.33
     데이터를
    2.22
    数据
    2.20
    データを
    2.19
    データ
    2.16
     डेटा
    2.13
     dữ
    2.03
     데이터
    1.99
    数据的
    1.99
    Act Density 0.249%

    No Known Activations