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

    Neuronpedia

    INDEX
    Explanations

    final answer marked by box

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ketika
    0.49
    řez
    0.47
    gger
    0.46
     iterates
    0.46
    ボール
    0.46
     коль
    0.45
     pada
    0.45
    orting
    0.44
     বিকেলে
    0.44
    তিপ
    0.44
    POSITIVE LOGITS
     viven
    0.69
     GDP
    0.68
     живут
    0.66
     SWOT
    0.66
     Religion
    0.65
     Kuna
    0.65
     religione
    0.65
     viviendo
    0.64
     USAID
    0.64
    Religion
    0.64
    Act Density 0.240%

    No Known Activations