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

    Neuronpedia

    INDEX
    Explanations

    my

    np_acts-logits-general · gemini-2.5-flash-lite

    discourse connectors and prepositional function words that signal relationships and structure within explanations or requests.

    oai_token-act-pair · gpt-5Triggered by @yooniel31
    New Auto-Interp
    Negative Logits
     وقلنا
    0.59
     recomendamos
    0.54
    ிறோம்
    0.53
     بدنا
    0.50
     расскажем
    0.50
     creemos
    0.49
    yoruz
    0.48
     قلنا
    0.46
    让你
    0.46
     شفنا
    0.46
    POSITIVE LOGITS
     my
    3.89
    我的
    3.78
     আমার
    3.47
     моих
    3.47
     мои
    3.45
     minha
    3.44
     моей
    3.44
     моего
    3.44
     mijn
    3.41
     моя
    3.31
    Act Density 0.554%

    No Known Activations