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

    Neuronpedia

    INDEX
    Explanations

    drainage and water flow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MARRI
    0.71
     निभाने
    0.62
     ngunit
    0.61
     dwie
    0.60
     dapat
    0.59
     kissed
    0.59
     culinary
    0.59
     என்பது
    0.59
     dwóch
    0.58
     Reigns
    0.58
    POSITIVE LOGITS
     drains
    1.00
    Drain
    0.98
     drainage
    0.96
    و
    0.95
    ل
    0.94
     Drainage
    0.93
     Drain
    0.91
    h
    0.88
    ו
    0.84
     drain
    0.82
    Act Density 0.017%

    No Known Activations