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

    Neuronpedia

    INDEX
    Explanations

    denial and disagreement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    我自己
    0.68
    нутри
    0.67
     interessante
    0.67
    /
    0.66
     مقدار
    0.66
     eines
    0.65
     fascinating
    0.65
     المزيد
    0.65
     lebih
    0.64
    полне
    0.64
    POSITIVE LOGITS
     lawmakers
    0.80
     정부
    0.77
     allegations
    0.73
     governments
    0.73
    政府
    0.72
     gunmen
    0.72
     legislators
    0.71
     dissidents
    0.71
     vigorously
    0.70
    government
    0.68
    Act Density 0.001%

    No Known Activations