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

    Neuronpedia

    INDEX
    Explanations

    past time indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kemarin
    0.57
    后来
    0.53
     ago
    0.52
     était
    0.49
     मैंने
    0.48
    Originally
    0.48
    後來
    0.47
     damals
    0.47
    ಲಾಯಿತು
    0.46
    was
    0.45
    POSITIVE LOGITS
     আগের
    0.52
     earlier
    0.52
    翌
    0.49
     годом
    0.48
     Earlier
    0.46
     прису
    0.43
     нака
    0.42
     Dart
    0.40
     anteriores
    0.40
    鍖
    0.39
    Act Density 0.008%

    No Known Activations