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

    Neuronpedia

    INDEX
    Explanations

    prepositions and articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tzw
    0.34
    ,?
    0.34
     Jamboree
    0.33
    Compose
    0.32
    -
    0.32
    [
    0.32
    <0xD9>
    0.32
     Bianchi
    0.32
     Deutsches
    0.31
     reinsurance
    0.31
    POSITIVE LOGITS
     مذکور
    0.46
     ಯಾವುದೇ
    0.43
     awọn
    0.42
     aliments
    0.40
    前記
    0.39
     Presumably
    0.37
     동일
    0.37
     각각
    0.36
    larghezza
    0.35
    奻
    0.35
    Act Density 0.226%

    No Known Activations