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

    Neuronpedia

    INDEX
    Explanations

    coordinates/matrix parsing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .mi
    -0.07
    бі
    -0.07
    .buy
    -0.07
     coco
    -0.07
     Tim
    -0.06
     Kafka
    -0.06
    etur
    -0.06
     这
    -0.06
    -my
    -0.06
    (as
    -0.06
    POSITIVE LOGITS
     DirectX
    0.07
    _exists
    0.06
    increase
    0.06
     روست
    0.06
     تخصص
    0.06
    صت
    0.06
     regular
    0.06
    unicipio
    0.06
    <Scalars
    0.06
    мотреть
    0.06
    Act Density 0.006%

    No Known Activations