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

    Neuronpedia

    INDEX
    Explanations

    before transformers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सहित
    0.46
     solamente
    0.44
    ：“
    0.44
     également
    0.44
    también
    0.43
    larım
    0.43
     Надо
    0.43
    ൮
    0.43
     również
    0.43
     усі
    0.43
    POSITIVE LOGITS
     economists
    0.46
     bureaucr
    0.45
     nonprofits
    0.45
     entrepreneurs
    0.45
     bureaucrats
    0.45
     innovators
    0.44
     politici
    0.44
     tribunals
    0.44
     architects
    0.43
     incumbents
    0.43
    Act Density 0.005%

    No Known Activations