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

    Neuronpedia

    INDEX
    Explanations

    countries and geography

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arrested
    0.84
    ikken
    0.83
     culminated
    0.81
     grenade
    0.80
    isição
    0.79
     related
    0.77
     intercept
    0.77
    elhos
    0.77
     intercepted
    0.76
     মনির
    0.76
    POSITIVE LOGITS
     Countries
    1.95
     countries
    1.95
     países
    1.87
    Countries
    1.83
     geography
    1.73
    countries
    1.69
     Geography
    1.67
    Geography
    1.64
     paesi
    1.60
     Mexico
    1.59
    Act Density 0.252%

    No Known Activations