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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     saints
    -0.07
    memory
    -0.07
    .node
    -0.07
    ована
    -0.06
    'en
    -0.06
    แหล
    -0.06
    PLACE
    -0.06
    Pretty
    -0.06
    athing
    -0.06
     IO
    -0.06
    POSITIVE LOGITS
     gigs
    0.07
     strand
    0.07
    <tag
    0.06
    找
    0.06
     verbally
    0.06
    ».
    0.06
     страш
    0.06
     cosa
    0.06
     상담
    0.06
    ».↵
    0.06
    Act Density 0.010%

    No Known Activations