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

    Neuronpedia

    INDEX
    Explanations

    Belarus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ق
    1.43
    ע
    1.42
    یه
    1.20
    ة
    1.11
    ן
    1.10
    ل
    1.09
    л
    1.09
    ት
    1.05
    ת
    1.03
    at
    1.00
    POSITIVE LOGITS
     అనేది
    0.87
    Belarus
    0.82
    AR
    0.81
    dioxide
    0.81
     Беларуси
    0.80
    COT
    0.78
     Belarus
    0.77
    iv
    0.76
    stadt
    0.76
    ্রের
    0.76
    Act Density 0.001%

    No Known Activations