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

    Neuronpedia

    INDEX
    Explanations

    places and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    What
    0.77
    How
    0.75
    Why
    0.69
    When
    0.60
    Definition
    0.59
    Introduction
    0.59
     How
    0.58
    Что
    0.58
    Myth
    0.57
    Advantages
    0.56
    POSITIVE LOGITS
     browse
    0.54
     Browse
    0.53
     search
    0.52
     $\$
    0.50
     browsing
    0.48
     مدينة
    0.48
    earch
    0.46
    owntown
    0.45
     town
    0.44
     담당
    0.44
    Act Density 0.005%

    No Known Activations