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

    Neuronpedia

    INDEX
    Explanations

    Punjab geography and institutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.79
    e
    0.75
    ي
    0.66
     that
    0.64
    with
    0.59
    1
    0.59
     الك
    0.59
     بأ
    0.59
     أ
    0.58
    '
    0.58
    POSITIVE LOGITS
    ियों
    0.72
    avila
    0.68
    ogical
    0.66
    ow
    0.62
    おしゃれ
    0.61
    㭋
    0.58
    ону
    0.58
    ु
    0.58
    ය
    0.57
    ע
    0.56
    Act Density 0.001%

    No Known Activations