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

    Neuronpedia

    INDEX
    Explanations

    shopping malls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ک
    0.70
    ۔
    0.59
    is
    0.58
    what
    0.57
    ال
    0.56
    types
    0.56
    on
    0.55
    yoga
    0.55
    واری
    0.55
    police
    0.54
    POSITIVE LOGITS
     malls
    0.93
     mall
    0.87
     Mall
    0.70
    Mall
    0.70
     MALL
    0.57
     मॉल
    0.57
    (
    0.57
     깜
    0.56
     IMAX
    0.55
     winkel
    0.54
    Act Density 0.001%

    No Known Activations