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

    Neuronpedia

    INDEX
    Explanations

    agreement and consensus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     জিজ্ঞাসাবাদ
    0.70
     pyramids
    0.69
     stalk
    0.69
     détour
    0.67
    hti
    0.67
    वीय
    0.67
    glichkeiten
    0.67
    subcategory
    0.67
     mistura
    0.66
     satir
    0.66
    POSITIVE LOGITS
     agree
    2.40
     agreement
    2.26
     Agreement
    2.09
     agreeing
    2.07
     agrees
    2.05
     Agree
    2.03
     agreed
    2.02
    agree
    1.98
    agreement
    1.87
     consensus
    1.86
    Act Density 0.311%

    No Known Activations