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

    Neuronpedia

    INDEX
    Explanations

    he

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fly
    -0.07
    руб
    -0.07
    Tipo
    -0.06
     velk
    -0.06
    Bookmark
    -0.06
    озможно
    -0.06
     oa
    -0.06
     gái
    -0.06
    .cid
    -0.06
     Chr
    -0.06
    POSITIVE LOGITS
     Jonah
    0.07
    acy
    0.06
    .invoke
    0.06
     centuries
    0.06
     Ama
    0.06
     transporting
    0.06
     criteria
    0.06
     archives
    0.06
     tweaked
    0.06
    Jobs
    0.06
    Act Density 0.053%

    No Known Activations