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

    Neuronpedia

    INDEX
    Explanations

    geographical or geopolitical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dengan
    1.27
    the
    1.26
    desde
    1.09
    AN
    1.09
    RE
    1.06
    year
    1.03
    with
    1.02
    geq
    1.02
    by
    1.01
    IPv
    1.01
    POSITIVE LOGITS
    ه
    1.23
     środow
    1.09
    ਾਈ
    1.02
    ക്കായി
    1.00
     Accepts
    0.99
    يطان
    0.99
    㡺
    0.98
    لین
    0.98
     Name
    0.96
     Второй
    0.96
    Act Density 0.000%

    No Known Activations