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

    Neuronpedia

    INDEX
    Explanations

    section titles and list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    是我们
    0.46
    我们的
    0.46
     teha
    0.46
    nBitCount
    0.45
     প্রবন্ধ
    0.44
     trusty
    0.43
    我们
    0.42
     我们
    0.42
    做好
    0.42
    ￳
    0.42
    POSITIVE LOGITS
     controversies
    0.55
    その他の
    0.52
     notables
    0.47
    バス
    0.47
     controversy
    0.47
     tentatives
    0.46
     notable
    0.46
    United
    0.46
     reports
    0.45
     hypotheses
    0.45
    Act Density 0.044%

    No Known Activations