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

    Neuronpedia

    INDEX
    Explanations

    nationalities followed by officials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     grim
    2.31
    zelfde
    2.13
    ان
    2.01
     famous
    1.83
    jší
    1.75
     familiar
    1.75
    ки
    1.74
    ००
    1.69
     eben
    1.68
     ct
    1.67
    POSITIVE LOGITS
    ivores
    1.98
    কোনও
    1.82
    crest
    1.81
    ships
    1.73
    াক্ত
    1.72
    முகச்
    1.70
    લ
    1.69
     країн
    1.67
    мут
    1.66
    🅽
    1.66
    Act Density 0.000%

    No Known Activations