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

    Neuronpedia

    INDEX
    Explanations

    active thinking, Esperanto

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    をクリック
    0.37
     عرضه
    0.36
     Gemma
    0.35
    ޢ
    0.35
     commemor
    0.35
    暊
    0.35
     Jank
    0.34
     grace
    0.34
     Mayor
    0.33
     paren
    0.33
    POSITIVE LOGITS
    yaar
    0.42
     아이
    0.42
     ప్రస్తుతం
    0.39
    ạch
    0.39
    бари
    0.39
    িলে
    0.37
    લાઈ
    0.37
     régionale
    0.37
    这将
    0.37
    𝚕
    0.37
    Act Density 0.000%

    No Known Activations