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

    Neuronpedia

    INDEX
    Explanations

    International references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     angi
    -0.09
    Contracts
    -0.08
    Advertising
    -0.08
     권
    -0.08
     Grö
    -0.08
    Deput
    -0.08
    嫌
    -0.08
     semifinal
    -0.08
    ẵn
    -0.08
    Kam
    -0.08
    POSITIVE LOGITS
     England
    0.15
     britannique
    0.13
    英国
    0.13
     British
    0.13
     Inglaterra
    0.12
     UK's
    0.12
     البريطانية
    0.12
     Britain
    0.12
     Britain's
    0.12
     британ
    0.12
    Act Density 0.303%

    No Known Activations