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

    Neuronpedia

    INDEX
    Explanations

    province

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Look
    -0.07
    ETA
    -0.07
     Eternal
    -0.06
     Interaction
    -0.06
     interaction
    -0.06
    arsing
    -0.06
     simulated
    -0.06
     catching
    -0.06
     accounting
    -0.06
     Eric
    -0.06
    POSITIVE LOGITS
     province
    0.12
     Province
    0.12
    Province
    0.12
     provinces
    0.10
    province
    0.09
     Provincial
    0.09
     provincia
    0.08
    ville
    0.08
    省
    0.08
     Prov
    0.08
    Act Density 0.008%

    No Known Activations