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

    Neuronpedia

    INDEX
    Explanations

    safeguarding, war, love, sunshine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ందో
    0.40
    andos
    0.40
     Slide
    0.39
    ഛ
    0.38
     ocurre
    0.38
    กรณ์
    0.38
     امشي
    0.38
    ضبط
    0.37
     repeat
    0.37
     повторя
    0.37
    POSITIVE LOGITS
     idd
    0.42
    Backend
    0.40
    path
    0.38
     რ
    0.38
     ?></
    0.38
     backend
    0.38
    估计
    0.38
     뒷
    0.38
     வல
    0.37
    Lung
    0.37
    Act Density 0.001%

    No Known Activations