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

    Neuronpedia

    INDEX
    Explanations

    code block delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     coverings
    0.32
     orthopedic
    0.30
    ropolit
    0.30
    ENES
    0.30
    צי
    0.30
     superhuman
    0.30
     ornamentation
    0.30
    Continue
    0.29
     ornaments
    0.29
    DIY
    0.28
    POSITIVE LOGITS
     ```
    0.84
    ```
    0.73
    <code>
    0.62
    #!/
    0.45
    if
    0.44
     mkdir
    0.42
     `<
    0.41
     //
    0.41
    代码
    0.41
    import
    0.40
    Act Density 0.135%

    No Known Activations