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

    Neuronpedia

    INDEX
    Explanations

    AI, chatbot, browser, character, box

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    0.41
    .
    0.40
    ։
    0.38
    ))
    0.37
    )))
    0.37
    ?,
    0.36
    ।
    0.35
    ',
    0.35
    ครับ
    0.34
     :
    0.33
    POSITIVE LOGITS
    នូវ
    0.44
     einen
    0.39
     υψη
    0.38
     sɛ
    0.38
     scalable
    0.38
     weatherproof
    0.38
    eine
    0.37
    最適な
    0.37
     bardziej
    0.37
    δει
    0.37
    Act Density 0.069%

    No Known Activations