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

    Neuronpedia

    INDEX
    Explanations

    extent (Similar inand intelligent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🔋
    0.56
    ی
    0.54
     مبنی
    0.53
    电池
    0.53
    電池
    0.51
    ،
    0.50
    II
    0.48
    padă
    0.48
    قی
    0.48
     شک
    0.48
    POSITIVE LOGITS
     week
    0.47
     hetzelfde
    0.47
    eday
    0.44
     ploch
    0.44
     weg
    0.43
     denn
    0.43
     produce
    0.43
     begrü
    0.43
     Empire
    0.42
     Klima
    0.42
    Act Density 0.001%

    No Known Activations