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

    Neuronpedia

    INDEX
    Explanations

    Research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    avi
    -0.07
    ecký
    -0.07
    Ana
    -0.06
     Ana
    -0.06
    ção
    -0.06
    õ
    -0.06
    ZONE
    -0.06
    oa
    -0.06
    oso
    -0.06
     nt
    -0.06
    POSITIVE LOGITS
    ارش
    0.07
     Leicester
    0.06
    .initializeApp
    0.06
    斯特
    0.06
     England
    0.06
     behalf
    0.06
     ／
    0.06
     граду
    0.06
    FXML
    0.06
    lust
    0.06
    Act Density 0.628%

    No Known Activations