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

    Neuronpedia

    INDEX
    Explanations

    foreign languages and text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deh
    0.70
    inha
    0.65
    在
    0.64
    ानंतर
    0.64
     iba
    0.64
     zahrani
    0.63
     brasileiros
    0.62
    们的
    0.60
    ங்களின்
    0.59
     ایرانی
    0.59
    POSITIVE LOGITS
    निष्ठ
    0.93
    Lil
    0.86
    language
    0.85
     리뷰
    0.85
    anguage
    0.84
    TodoList
    0.84
    speakers
    0.84
     текст
    0.83
    tense
    0.82
    loser
    0.82
    Act Density 0.327%

    No Known Activations