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

    Neuronpedia

    INDEX
    Explanations

    port numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     God
    0.67
     Powered
    0.67
     kub
    0.66
     congreg
    0.66
     munt
    0.66
     DHCP
    0.64
     TVs
    0.63
     Bringing
    0.63
     dressed
    0.63
     buff
    0.63
    POSITIVE LOGITS
    端口
    1.04
    port
    1.01
    Port
    0.98
    ポート
    0.97
    PORT
    0.94
     ports
    0.90
     port
    0.89
     puertos
    0.88
    porta
    0.86
    oport
    0.85
    Act Density 0.047%

    No Known Activations