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
     verilm
    -0.07
    ože
    -0.07
     celkem
    -0.06
    (NUM
    -0.06
     Broker
    -0.06
    огра
    -0.06
     أص
    -0.06
     DEF
    -0.06
     gab
    -0.06
    drivers
    -0.06
    POSITIVE LOGITS
    ">'
    0.08
    _formatted
    0.06
    aside
    0.06
     щоб
    0.06
    ```
    0.06
     dele
    0.06
     `\
    0.06
     onStart
    0.06
    คน
    0.06
    短
    0.06
    Act Density 0.125%

    No Known Activations