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

    Neuronpedia

    INDEX
    Explanations

    collection department

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    削除
    0.47
    分裂
    0.45
    返品
    0.45
    分割
    0.45
    padding
    0.44
    お金
    0.44
    OM
    0.43
     පු
    0.43
     ಹಣ
    0.43
     ದೇಹ
    0.43
    POSITIVE LOGITS
     niektórych
    0.50
     Audrey
    0.49
     nejen
    0.49
     some
    0.47
     musically
    0.46
     most
    0.45
     Learned
    0.43
     alten
    0.43
     non
    0.43
     nos
    0.43
    Act Density 0.004%

    No Known Activations