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

    Neuronpedia

    INDEX
    Explanations

    New York Times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সকল
    0.54
     পরবর্তীতে
    0.52
     specular
    0.52
     kiddos
    0.52
     HDD
    0.51
     উক্ত
    0.50
     NodeJS
    0.49
     impacted
    0.48
    Unfortunately
    0.48
     aufgrund
    0.48
    POSITIVE LOGITS
    nytimes
    1.02
     nyt
    0.83
    nyt
    0.80
     न्यूयॉर्क
    0.75
    ニューヨーク
    0.70
     advisers
    0.67
    Reuters
    0.67
    纽约
    0.66
     Qaeda
    0.66
     NPR
    0.66
    Act Density 0.008%

    No Known Activations