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

    Neuronpedia

    INDEX
    Explanations

    key component or takeaway

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     certaine
    0.93
     qualche
    0.87
    situation
    0.81
     tertentu
    0.81
    某一
    0.79
     keadaan
    0.79
    某些
    0.78
     çeşitli
    0.77
    possible
    0.77
    特定の
    0.76
    POSITIVE LOGITS
     ingredient
    1.15
     differentiator
    1.15
     takeaway
    1.14
     contributors
    1.11
     players
    1.08
     components
    1.06
     ingredients
    1.06
     tenets
    1.03
     determinant
    1.03
     takeaways
    1.02
    Act Density 0.729%

    No Known Activations