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

    Neuronpedia

    INDEX
    Explanations

    million/billion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ske
    -0.07
     mundo
    -0.07
     jumper
    -0.07
    _KEY
    -0.06
    licts
    -0.06
    연구
    -0.06
    CREEN
    -0.06
    orna
    -0.06
     dns
    -0.06
     helpers
    -0.06
    POSITIVE LOGITS
    .Interval
    0.07
     расход
    0.06
    .Ent
    0.06
    (bottom
    0.06
    ",[
    0.06
     ]).
    0.06
    -million
    0.06
     */)
    0.06
     BI
    0.06
    }'",
    0.06
    Act Density 0.013%

    No Known Activations