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

    Neuronpedia

    INDEX
    Explanations

    historic periods and centuries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     delete
    0.80
    プライ
    0.78
     eyeshadow
    0.75
     액
    0.71
     అరుణ
    0.71
     deletes
    0.69
     taco
    0.69
     नोएडा
    0.69
     helpline
    0.68
     TPU
    0.68
    POSITIVE LOGITS
     nineteenth
    2.32
     medieval
    2.29
     Medieval
    2.12
     centuries
    2.05
    Medieval
    2.02
     Nineteenth
    1.98
     eighteenth
    1.98
     colonial
    1.97
    medieval
    1.91
     colonialism
    1.85
    Act Density 0.270%

    No Known Activations