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

    Neuronpedia

    INDEX
    Explanations

    characters and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    3
    0.49
    puts
    0.46
    ES
    0.45
     lays
    0.45
    Q
    0.45
     straps
    0.44
    4
    0.44
    ESS
    0.44
    6
    0.42
    INT
    0.42
    POSITIVE LOGITS
    ूरत
    0.49
     असल्यास
    0.48
    rvGroup
    0.48
    りたい
    0.47
    乘坐
    0.47
    arım
    0.47
     Vậy
    0.46
     کریم
    0.46
    沙发
    0.46
    tFileInputExcel
    0.45
    Act Density 0.002%

    No Known Activations