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

    Neuronpedia

    INDEX
    Explanations

    names of people and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tains
    0.31
    வசம்
    0.29
     usted
    0.29
     Toutes
    0.29
    您
    0.28
    User
    0.28
     तरीका
    0.27
     MSRP
    0.27
     എല്ലാം
    0.27
    getValue
    0.27
    POSITIVE LOGITS
    n
    0.29
    ara
    0.23
    l
    0.23
    лини
    0.23
    ↵↵
    0.22
    nagar
    0.22
    。
    0.22
    lake
    0.22
    (
    0.22
     kerjasama
    0.22
    Act Density 0.021%

    No Known Activations