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

    Neuronpedia

    INDEX
    Explanations

    to provide and help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     runny
    0.29
     memos
    0.26
     downloads
    0.25
    =
    0.25
    前提
    0.25
     resized
    0.25
     ./
    0.25
     [])
    0.25
     collectibles
    0.25
     primaries
    0.25
    POSITIVE LOGITS
     помога
    0.35
     максимально
    0.32
     asegurarse
    0.32
     помочь
    0.31
    improve
    0.31
     profundizar
    0.29
     reinvigor
    0.29
     допомогти
    0.29
    Improve
    0.29
     migliorare
    0.29
    Act Density 0.363%

    No Known Activations