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

    Neuronpedia

    INDEX
    Explanations

    durante

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     more
    1.06
    more
    0.86
     three
    0.79
     birkaç
    0.77
     seul
    0.77
     cinq
    0.76
     etiam
    0.75
     गोरखपुर
    0.74
     centuries
    0.74
     soon
    0.74
    POSITIVE LOGITS
    Tokens
    0.90
     PBMCs
    0.81
     Bowers
    0.81
    Jobs
    0.81
    @@
    0.80
     Brows
    0.79
     Pants
    0.77
     Tutorials
    0.77
    Books
    0.77
     Jewelry
    0.76
    Act Density 0.001%

    No Known Activations