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

    Neuronpedia

    INDEX
    Explanations

    urban vs rural and related contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    g
    1.61
    d
    1.20
    خ
    1.04
     of
    1.02
    x
    1.01
    p
    1.00
    م
    0.99
    of
    0.99
    l
    0.95
    c
    0.95
    POSITIVE LOGITS
    ;
    1.03
    ?
    0.82
     urban
    0.82
     urbana
    0.81
    :
    0.77
    <0x80>
    0.74
     cityscape
    0.74
    >
    0.73
    ми
    0.71
    <0xBF>
    0.70
    Act Density 0.008%

    No Known Activations