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

    Neuronpedia

    INDEX
    Explanations

    compound word beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gaussian
    0.29
    バイト
    0.28
    ্ের
    0.28
    Despatx
    0.27
    sigmaf
    0.26
    پے
    0.26
    酵素
    0.26
    aliyet
    0.26
     بالټ
    0.25
     فونبټ
    0.25
    POSITIVE LOGITS
    -
    0.34
     sorts
    0.25
    ванта
    0.25
    Jo
    0.24
     artis
    0.24
     regards
    0.24
     jorn
    0.24
     leps
    0.23
    。「
    0.23
     environments
    0.23
    Act Density 1.081%

    No Known Activations