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

    Neuronpedia

    INDEX
    Explanations

    thank you for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bytes
    0.48
    माम
    0.47
    تم
    0.46
    מו
    0.46
    Avi
    0.45
    (
    0.45
    떼
    0.45
    ך
    0.44
     ڈال
    0.44
    [
    0.44
    POSITIVE LOGITS
     evidently
    0.52
    我认为
    0.52
    eniu
    0.50
     வாய்ப்ப
    0.50
     abreast
    0.50
     Belief
    0.50
     karakteristik
    0.50
     amplifying
    0.49
     alternatif
    0.49
     facet
    0.48
    Act Density 0.004%

    No Known Activations