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

    Neuronpedia

    INDEX
    Explanations

    Salesforce Code, two characters, the Plaintiff

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     അടു
    0.37
    õe
    0.36
     réf
    0.35
    PrefabAsset
    0.35
    銨
    0.35
    iol
    0.34
    ฎ
    0.34
    Ϫ
    0.34
     kuće
    0.33
    ടക
    0.33
    POSITIVE LOGITS
     Stephenson
    0.42
    PHONY
    0.40
     ငါ
    0.40
     宝宝
    0.40
     Shawn
    0.40
     Mannheim
    0.40
     Torr
    0.39
    fib
    0.38
     Kearns
    0.38
    बांध
    0.38
    Act Density 0.000%

    No Known Activations