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

    Neuronpedia

    INDEX
    Explanations

    work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Spicer
    -0.07
    (unit
    -0.07
    Rock
    -0.06
     transporte
    -0.06
     تف
    -0.06
    贵
    -0.06
    Fly
    -0.06
     Less
    -0.06
    ROUND
    -0.06
     gas
    -0.06
    POSITIVE LOGITS
    .clients
    0.06
     çalışan
    0.06
    ानन
    0.06
     Macron
    0.06
     genomic
    0.06
     incid
    0.06
    дина
    0.06
    .additional
    0.06
     Barbar
    0.05
     credits
    0.05
    Act Density 0.088%

    No Known Activations