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

    Neuronpedia

    INDEX
    Explanations

    headers and footers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     एक्सप्ले
    0.39
    valent
    0.38
    ଢ
    0.37
    անդ
    0.36
    ამდე
    0.35
    ಾ
    0.35
    webapp
    0.35
    𝚣
    0.35
    卡
    0.35
     erklären
    0.34
    POSITIVE LOGITS
     Footer
    0.80
     footer
    0.79
    Footer
    0.71
     页
    0.70
     header
    0.69
     Header
    0.68
     headers
    0.68
     foot
    0.65
    页
    0.65
    Header
    0.64
    Act Density 0.004%

    No Known Activations