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

    Neuronpedia

    INDEX
    Explanations

    code and command examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.74
     •
    0.73
    ・
    0.73
    ]-
    0.72
    |-
    0.71
    _{+}-
    0.71
    loat
    0.71
     side
    0.70
     sied
    0.69
     ・
    0.69
    POSITIVE LOGITS
    ```
    1.09
     ```
    1.01
    ```{
    0.70
    ``
    0.69
    权力
    0.69
    <code>
    0.69
    Wing
    0.67
    肌肉
    0.67
    Jewish
    0.67
    JAK
    0.66
    Act Density 0.142%

    No Known Activations