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

    Neuronpedia

    INDEX
    Explanations

    run and press

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ekonomik
    0.49
     unhappiness
    0.44
     ambito
    0.39
     League
    0.39
     jurídico
    0.37
     fairer
    0.37
     آیات
    0.37
     Darüber
    0.37
     invertebrates
    0.37
     экономической
    0.37
    POSITIVE LOGITS
     voila
    0.77
     voilà
    0.68
    就可以了
    0.67
    即可
    0.64
    あとは
    0.62
    就行
    0.57
     Enjoy
    0.52
    然後
    0.52
    然后
    0.50
     then
    0.50
    Act Density 0.075%

    No Known Activations