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

    Neuronpedia

    INDEX
    Explanations

    setup, oversaturated, super user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     public
    0.45
     matcher
    0.45
    ুলে
    0.45
     объеди
    0.45
     polymorphic
    0.44
     rectMode
    0.43
     maximizes
    0.43
     phường
    0.42
    োজেন
    0.41
    ↵
    0.41
    POSITIVE LOGITS
    ق
    0.43
    a
    0.43
    ao
    0.42
    \|
    0.42
    kali
    0.42
    د
    0.42
     Acrobat
    0.41
     Superstar
    0.41
    }\,
    0.40
    nake
    0.40
    Act Density 0.001%

    No Known Activations