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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     repro
    -0.08
    グ
    -0.08
    ]):
↵
    -0.07
    ğer
    -0.07
     :-↵
    -0.06
     Guil
    -0.06
    FileInfo
    -0.06
     вихов
    -0.06
    RV
    -0.06
     ":
    -0.06
    POSITIVE LOGITS
    riters
    0.07
     Columbus
    0.06
     insurgents
    0.06
     conferred
    0.06
     Από
    0.06
     tất
    0.06
    .jobs
    0.06
    昨
    0.06
    (Item
    0.06
     Attack
    0.06
    Act Density 0.109%

    No Known Activations