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

    Neuronpedia

    INDEX
    Explanations

    vehicle, book, directed, atoms, Boxes, yard, IA, Earbuds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⴽ
    0.40
     দেখুনঃ
    0.39
    케
    0.39
    룬
    0.39
    ធម្ម
    0.38
    뤽
    0.38
    ле
    0.37
    ū
    0.37
    ↠
    0.37
    پاک
    0.37
    POSITIVE LOGITS
     tuo
    0.43
     beho
    0.42
     natal
    0.40
     slat
    0.40
     звезда
    0.39
     anion
    0.39
     custody
    0.39
     sul
    0.38
     scut
    0.38
     అమ్మ
    0.38
    Act Density 0.000%

    No Known Activations