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

    Neuronpedia

    INDEX
    Explanations

    has to offer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सेक्शन
    0.41
    知的
    0.41
     XLR
    0.38
     शकता
    0.38
     fáciles
    0.38
     consid
    0.37
     trouverez
    0.37
     الوزراء
    0.36
     helst
    0.36
    ignés
    0.36
    POSITIVE LOGITS
     offer
    0.54
    Offer
    0.52
    offer
    0.50
     aportar
    0.47
     aport
    0.44
     aporte
    0.43
    Has
    0.43
    teach
    0.43
     aporta
    0.42
     Offer
    0.41
    Act Density 0.004%

    No Known Activations