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

    Neuronpedia

    INDEX
    Explanations

    respond

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     centroid
    -0.07
    اده
    -0.06
    icious
    -0.06
     gh
    -0.06
     elephant
    -0.06
     такие
    -0.06
    OUGH
    -0.06
     fertile
    -0.06
    vé
    -0.06
    ;;
    -0.06
    POSITIVE LOGITS
    (bs
    0.07
     JButton
    0.07
     LoginPage
    0.07
    ‌شوند
    0.07
    .provider
    0.07
    (GameObject
    0.07
    .notifyDataSetChanged
    0.07
    (ts
    0.06
     reps
    0.06
    (pat
    0.06
    Act Density 0.002%

    No Known Activations