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

    Neuronpedia

    INDEX
    Explanations

    include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ocker
    -0.07
    edReader
    -0.07
    מדי
    -0.07
     redis
    -0.07
     python
    -0.06
    Along
    -0.06
    降低
    -0.06
    以及其他
    -0.06
     amphib
    -0.06
     reversed
    -0.06
    POSITIVE LOGITS
    家园
    0.08
    movement
    0.08
    capacity
    0.07
     setups
    0.07
    //------------------------------------------------------------------------------------------------
    0.07
     Stay
    0.07
     '-';↵
    0.07
     MUST
    0.07
    JECT
    0.07
     Pussy
    0.07
    Act Density 0.025%

    No Known Activations