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

    Neuronpedia

    INDEX
    Explanations

    k

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aggi
    -0.07
    الي
    -0.07
    tera
    -0.06
    eric
    -0.06
    Send
    -0.06
    لق
    -0.06
    究
    -0.06
    藤
    -0.06
     organisation
    -0.06
     네
    -0.06
    POSITIVE LOGITS
    handlers
    0.07
    293
    0.07
     Computer
    0.06
    SupportedException
    0.06
     soak
    0.06
    weeks
    0.06
     Emmy
    0.06
    **)&
    0.06
     вполне
    0.06
    299
    0.06
    Act Density 0.004%

    No Known Activations