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

    Neuronpedia

    INDEX
    Explanations

    multiple languages and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aqui
    0.52
     janvier
    0.46
     now
    0.45
    I
    0.44
     mood
    0.44
    م
    0.44
     here
    0.43
     of
    0.43
     I
    0.42
     Income
    0.42
    POSITIVE LOGITS
     ausschließlich
    0.54
    并通过
    0.52
     以及
    0.45
    以及
    0.44
     বলেছিলেন
    0.43
     উদ্দেশ্যে
    0.43
    🌯
    0.42
    ＿＿
    0.42
    🫢
    0.42
     እንዲሁም
    0.42
    Act Density 0.011%

    No Known Activations