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

    Neuronpedia

    INDEX
    Explanations

    information about Paris

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    0.95
    س
    0.70
    i
    0.65
    т
    0.63
    m
    0.61
    ي
    0.60
    ش
    0.57
    स
    0.56
    る
    0.55
    es
    0.55
    POSITIVE LOGITS
     conceivably
    0.57
     znacznie
    0.51
     znacz
    0.51
     incite
    0.46
     conceivable
    0.46
     berupa
    0.45
     buckwheat
    0.45
    Ｉ
    0.45
     স্থাপিত
    0.45
     stanowi
    0.44
    Act Density 0.001%

    No Known Activations