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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bulk
    -0.08
     fishes
    -0.08
     pł
    -0.07
     versus
    -0.07
     tej
    -0.07
    /pi
    -0.07
     pur
    -0.07
    /card
    -0.07
    enger
    -0.07
     급
    -0.07
    POSITIVE LOGITS
    .events
    0.11
    езде
    0.10
     ახლა
    0.10
     جڏهن
    0.09
     როდესაც
    0.09
     მაგალითად
    0.09
    ურნალ
    0.09
     როცა
    0.09
    ազգային
    0.09
     ആദ
    0.09
    Act Density 0.001%

    No Known Activations