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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aslında
    -0.07
     있던
    -0.06
    業務
    -0.06
    bi
    -0.06
    сам
    -0.06
     wildcard
    -0.06
    (names
    -0.06
    ('<
    -0.06
    éd
    -0.06
    �件
    -0.05
    POSITIVE LOGITS
     etwa
    0.08
     CASE
    0.07
    .Contact
    0.06
     паци
    0.06
     cases
    0.06
     nghiên
    0.06
    提示
    0.06
    uellen
    0.06
    :maj
    0.06
    >Select
    0.06
    Act Density 0.005%

    No Known Activations