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

    Neuronpedia

    INDEX
    Explanations

    user input prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <sub>
    0.40
    W
    0.40
    title
    0.39
    \*
    0.38
     লিপিবদ্ধ
    0.38
    B
    0.38
    レ
    0.38
    <sup>
    0.37
    ひ
    0.37
    header
    0.37
    POSITIVE LOGITS
    ovjek
    0.42
    putnik
    0.41
    ર્ગ
    0.40
    ៤
    0.40
    ๅ
    0.39
    🦳
    0.39
     गोविंद
    0.39
    鸦
    0.38
     ৃ
    0.38
     άνθρω
    0.38
    Act Density 0.002%

    No Known Activations