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

    Neuronpedia

    INDEX
    Explanations

    countries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Фургала
    0.40
     degrés
    0.38
     सरल
    0.38
     Ghanaian
    0.38
    δο
    0.36
     характера
    0.36
     оши
    0.36
     ذریعے
    0.36
     meaningless
    0.36
     Hessian
    0.35
    POSITIVE LOGITS
    Russia
    0.59
    🇮
    0.55
    देश
    0.52
    🇹
    0.52
    वर्ष
    0.51
     Cumhur
    0.50
     देश
    0.49
    一
    0.48
    country
    0.48
    ans
    0.47
    Act Density 0.035%

    No Known Activations