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

    Neuronpedia

    INDEX
    Explanations

    numbered lists and bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    সজ্জিত
    0.29
     اولا
    0.28
    ێنی
    0.28
    ڽ
    0.28
     sieve
    0.28
    दीश
    0.28
     komma
    0.28
     челу
    0.28
    ণ্ঠে
    0.28
    ␊
    0.27
    POSITIVE LOGITS
    <h2>
    0.42
    Another
    0.40
    <h3>
    0.39
     Another
    0.35
    ↵↵
    0.33
    ##
    0.31
    ation
    0.30
     Second
    0.30
     Secondly
    0.30
    b
    0.29
    Act Density 0.073%

    No Known Activations