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

    Neuronpedia

    INDEX
    Explanations

    directional geographical regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tất
    0.78
     Indies
    0.78
     metropolis
    0.75
     Paris
    0.74
     Americas
    0.73
     Manila
    0.73
     நகரம்
    0.73
     Jakarta
    0.71
     রাজধান
    0.70
     রাজধানীতে
    0.69
    POSITIVE LOGITS
     central
    1.97
     southern
    1.81
    central
    1.76
     southwestern
    1.73
     northern
    1.72
     southeastern
    1.71
     northwestern
    1.71
     northeastern
    1.67
     eastern
    1.65
    southern
    1.65
    Act Density 0.094%

    No Known Activations