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

    Neuronpedia

    INDEX
    Explanations

    Question and answer forum

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Drinks
    -0.07
    支
    -0.07
     Judy
    -0.06
     Oven
    -0.06
    _SORT
    -0.06
     Truck
    -0.06
     바로
    -0.06
     Metals
    -0.06
     Spin
    -0.06
    (and
    -0.06
    POSITIVE LOGITS
    =node
    0.07
     �
    0.07
     cur
    0.07
    /User
    0.07
    -message
    0.07
    getDefault
    0.06
     parked
    0.06
     govern
    0.06
     drib
    0.06
    )!↵
    0.06
    Act Density 0.006%

    No Known Activations