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

    Neuronpedia

    INDEX
    Explanations

    user prompts, questions, or commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᾷ
    0.29
    ).\\
    0.28
     $)$.
    0.27
     ruthenium
    0.27
    <unused2174>
    0.27
     SQLException
    0.27
    )})$
    0.27
    了不少
    0.26
    )».
    0.26
    ֩
    0.26
    POSITIVE LOGITS
    Here
    0.58
    ```
    0.54
    ##
    0.52
    OK
    0.47
    **
    0.46
    Can
    0.46
    Thank
    0.46
    Okay
    0.46
    Name
    0.46
    https
    0.45
    Act Density 0.217%

    No Known Activations