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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals and entities in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Binh Phan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cost
    -0.47
     Cost
    -0.45
    Effect
    -0.38
     Hej
    -0.38
     sevi
    -0.38
     CITY
    -0.38
     city
    -0.38
    City
    -0.38
     City
    -0.37
    city
    -0.37
    POSITIVE LOGITS
     phân
    2.59
    Phân
    1.45
     phan
    1.00
    분
    0.98
     분
    0.93
     Phan
    0.84
    phan
    0.84
    Phan
    0.74
     分
    0.74
    ÂN
    0.65
    Act Density 0.001%

    No Known Activations