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

    Neuronpedia

    INDEX
    Explanations

    political or governmental terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻷ
    0.70
    ｨ
    0.65
     е
    0.65
    fica
    0.64
     Несмотря
    0.63
     возраст
    0.62
    пра
    0.60
    োহণ
    0.60
     вот
    0.59
    োগ্য
    0.59
    POSITIVE LOGITS
    вання
    0.68
    impero
    0.67
     संविधान
    0.61
     partito
    0.61
    als
    0.60
    imiz
    0.60
    diction
    0.60
    力
    0.59
    ishly
    0.59
    دون
    0.59
    Act Density 0.002%

    No Known Activations