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

    Neuronpedia

    INDEX
    Explanations

    Portuguese

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    핀
    -0.06
    476
    -0.06
    uese
    -0.06
    pus
    -0.06
    ansom
    -0.06
    902
    -0.06
    ilateral
    -0.06
    ickest
    -0.06
     пы
    -0.06
    واء
    -0.06
    POSITIVE LOGITS
     Providers
    0.07
     battleground
    0.07
     Wrong
    0.06
    label
    0.06
     declaring
    0.06
     Yelp
    0.06
     rocky
    0.06
     Saddam
    0.06
     Essay
    0.06
    DataRow
    0.06
    Act Density 0.010%

    No Known Activations