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

    Neuronpedia

    INDEX
    Explanations

    update

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    封装
    0.39
    چین
    0.39
    indent
    0.38
    颶
    0.38
    naming
    0.37
     multipurpose
    0.36
    tes
    0.36
    iname
    0.36
    [,,"
    0.36
    结
    0.36
    POSITIVE LOGITS
     updates
    0.76
     update
    0.73
    更新
    0.70
     updated
    0.69
     Update
    0.68
     обновления
    0.66
     Updates
    0.65
     अपडेट
    0.65
     updating
    0.64
     обнов
    0.62
    Act Density 0.060%

    No Known Activations