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

    Neuronpedia

    INDEX
    Explanations

    cl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     moms
    -0.07
     chim
    -0.07
    annya
    -0.07
    stime
    -0.07
    mutation
    -0.06
     вывод
    -0.06
    umu
    -0.06
     آدم
    -0.06
     wed
    -0.06
     rin
    -0.06
    POSITIVE LOGITS
    대학교
    0.07
    К
    0.06
     KeyValuePair
    0.06
    .pack
    0.06
    neğin
    0.06
    ськ
    0.06
     (^
    0.06
    .Large
    0.06
    .desc
    0.06
    ">'↵
    0.06
    Act Density 0.001%

    No Known Activations