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

    Neuronpedia

    INDEX
    Explanations

    deportation, asylum, detention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pastel
    0.47
     Carl
    0.45
     Ta
    0.45
     작업
    0.45
     trabaj
    0.44
     Think
    0.44
     Sew
    0.44
     Christina
    0.44
     tầng
    0.44
     Yeast
    0.44
    POSITIVE LOGITS
     deportation
    0.86
     deport
    0.73
     extradition
    0.64
     deported
    0.63
     Deport
    0.57
     detainees
    0.57
     asylum
    0.53
     repatriation
    0.53
     detention
    0.52
    Afghanistan
    0.52
    Act Density 0.022%

    No Known Activations