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

    Neuronpedia

    INDEX
    Explanations

    code structure and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     வெற்ற
    0.42
    (@"
    0.41
    तरी
    0.40
     tengah
    0.39
     घरों
    0.39
    ার
    0.39
    шення
    0.38
    缨
    0.38
    гой
    0.38
    Vert
    0.38
    POSITIVE LOGITS
     '__
    0.42
     "_
    0.42
     extravagant
    0.39
     facts
    0.39
     '_
    0.38
     "__
    0.37
     "#
    0.37
     broken
    0.37
     "${
    0.37
     ધ્યાન
    0.37
    Act Density 0.001%

    No Known Activations