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

    Neuronpedia

    INDEX
    Explanations

    fictional places and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (/
    0.84
    欉
    0.81
     ПО
    0.79
     /
    0.78
    或
    0.76
     ~/
    0.76
     அல்லது
    0.76
     또는
    0.75
    嗗
    0.75
     வால்
    0.74
    POSITIVE LOGITS
     Fiction
    0.93
     Kedua
    0.92
     Mundial
    0.90
     Oldborough
    0.89
    Z
    0.88
    Year
    0.85
     Manufact
    0.85
     Consortium
    0.85
     dritten
    0.85
     Z
    0.84
    Act Density 0.121%

    No Known Activations