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

    Neuronpedia

    INDEX
    Explanations

    data structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Italy
    -0.06
    র
    -0.06
    �
    -0.06
     Jing
    -0.06
    <pcl
    -0.06
    ंय
    -0.06
     salads
    -0.06
     Mits
    -0.06
     Sty
    -0.06
    Compute
    -0.06
    POSITIVE LOGITS
     brilliantly
    0.07
    ồi
    0.07
     successful
    0.07
    height
    0.06
    cerer
    0.06
     summarized
    0.06
     setback
    0.06
     skvěl
    0.06
    postalcode
    0.06
     encrypt
    0.06
    Act Density 0.016%

    No Known Activations