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

    Neuronpedia

    INDEX
    Explanations

    tar sands and pipelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     چنان
    0.43
     Orsay
    0.39
     analges
    0.39
     জটিল
    0.38
     Reim
    0.38
     أكتوبر
    0.37
     reim
    0.37
     BOD
    0.37
     ParkingLot
    0.37
     onset
    0.37
    POSITIVE LOGITS
     tar
    1.04
     Keystone
    0.91
    tar
    0.89
     Tar
    0.80
    Tar
    0.80
     bitumen
    0.77
     tars
    0.74
     pipeline
    0.72
    pipeline
    0.70
     pipelines
    0.67
    Act Density 0.005%

    No Known Activations