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

    Neuronpedia

    INDEX
    Explanations

    concepts and contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    راط
    0.48
    ",{
    0.44
    нее
    0.43
    বাস
    0.43
    ayın
    0.42
    ιον
    0.42
    لس
    0.42
    เป็น
    0.42
    επ
    0.42
    <&
    0.42
    POSITIVE LOGITS
     spliced
    0.55
     plains
    0.46
     December
    0.44
     পানির
    0.43
     mann
    0.43
     Mazda
    0.43
     stitched
    0.43
     combustion
    0.42
     recursion
    0.42
     haka
    0.42
    Act Density 0.000%

    No Known Activations