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

    Neuronpedia

    INDEX
    Explanations

    citations and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BBQ
    0.75
     #
    0.66
     EVs
    0.64
     HOA
    0.61
     Premium
    0.60
    verages
    0.60
     Magento
    0.59
     WoW
    0.58
     outperforms
    0.57
     depress
    0.57
    POSITIVE LOGITS
     প্রমুখ
    0.89
    bibliothek
    0.86
     ശേഖ
    0.79
     başkan
    0.77
    などの
    0.75
     bibliographic
    0.73
     secrétaire
    0.73
     ওরফে
    0.72
     Bundan
    0.71
    などが
    0.70
    Act Density 0.000%

    No Known Activations