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

    Neuronpedia

    INDEX
    Explanations

    country or region

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sadness
    0.52
     의
    0.50
     tipo
    0.49
     propositional
    0.49
     の
    0.48
     redness
    0.48
     vous
    0.48
     einer
    0.48
    ใช้
    0.47
     bacter
    0.47
    POSITIVE LOGITS
     countries
    1.01
    ប្រទេស
    0.99
    Europe
    0.98
    Mexico
    0.97
     Europe
    0.96
     países
    0.96
    Australia
    0.96
    countries
    0.95
     Mexico
    0.95
    Canada
    0.93
    Act Density 0.014%

    No Known Activations