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

    Neuronpedia

    INDEX
    Explanations

    Here's a breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alanine
    0.26
     सामग्री
    0.25
     broadcasts
    0.25
    циями
    0.25
     regimens
    0.24
     LEC
    0.24
     possibilités
    0.24
     mette
    0.24
    穸
    0.23
     ά
    0.23
    POSITIVE LOGITS
     nejen
    0.29
    1
    0.27
    しかし
    0.26
    Además
    0.26
    ike
    0.25
    ='
    0.25
    However
    0.25
    o
    0.25
     inoltre
    0.25
    lem
    0.25
    Act Density 0.066%

    No Known Activations