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

    Neuronpedia

    INDEX
    Explanations

    `@` package names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iving
    0.85
    ร์
    0.70
    شی
    0.67
    িং
    0.67
    uring
    0.65
    𝙛
    0.64
    𝙝
    0.64
    ു
    0.63
    azy
    0.63
    illow
    0.63
    POSITIVE LOGITS
    ../
    0.69
    Correct
    0.66
     Muhammadu
    0.64
    Thời
    0.64
    %>%
    0.63
    Foi
    0.63
    ../../
    0.63
    0.62
    ㊗
    0.60
     Anambra
    0.60
    Act Density 0.006%

    No Known Activations