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

    Neuronpedia

    INDEX
    Explanations

    Religion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    สด
    -0.06
    wendung
    -0.06
     ředitel
    -0.06
    trfs
    -0.06
    據
    -0.06
     uphol
    -0.06
    Không
    -0.06
     indigenous
    -0.06
    lığın
    -0.06
     rubble
    -0.06
    POSITIVE LOGITS
     Оп
    0.08
    )、
    0.06
     arg
    0.06
    _ge
    0.06
     سخت
    0.06
    _hand
    0.06
     เร
    0.06
    .are
    0.06
     Τε
    0.06
     QUEUE
    0.06
    Act Density 0.018%

    No Known Activations