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

    Neuronpedia

    INDEX
    Explanations

    restaurant reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Des
    -0.09
     کمک
    -0.09
     Census
    -0.08
    cando
    -0.08
     τέλος
    -0.08
    .`|`↵
    -0.08
     Deployment
    -0.08
     aid
    -0.08
     WINAPI
    -0.08
     Implant
    -0.08
    POSITIVE LOGITS
     pastries
    0.12
    套餐
    0.12
    特色
    0.11
     smoked
    0.11
     блюда
    0.11
     roasted
    0.11
     स्वाद
    0.10
     sandwiches
    0.10
     salads
    0.10
     pizzas
    0.10
    Act Density 0.111%

    No Known Activations