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

    Neuronpedia

    INDEX
    Explanations

    set to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    createInfo
    0.78
    ValArr
    0.77
    ಳ್
    0.76
     जानकारियां
    0.74
    <unused1863>
    0.73
    沇
    0.72
    ურთიერთ
    0.72
    তোমার
    0.72
    វត្ត
    0.72
    detailID
    0.72
    POSITIVE LOGITS
     to
    0.92
     To
    0.83
    设置为
    0.79
     menjadi
    0.77
    to
    0.77
     become
    0.76
     xuống
    0.76
     becomes
    0.75
    改为
    0.73
    ให้
    0.72
    Act Density 0.262%

    No Known Activations