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

    Neuronpedia

    INDEX
    Explanations

    chemical functional groups and prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ෲ
    0.37
     GOODS
    0.35
     indiqu
    0.34
     wirtschaft
    0.33
     literatura
    0.33
     শাজ
    0.33
     ekonomik
    0.33
     ekonom
    0.32
     çeşitli
    0.32
    िरिक्स
    0.32
    POSITIVE LOGITS
    -
    0.47
    ths
    0.31
    фи
    0.29
    ск
    0.29
    -"
    0.28
    -#
    0.28
    rate
    0.28
     romanos
    0.28
    create
    0.28
    cel
    0.28
    Act Density 0.006%

    No Known Activations